© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 559
    Prev
    Next
    INDEX
    Explanations

    numerical code sequences and their associated attributes within data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hexadecimal numbers.

    oai_token-act-pair · gemini-1.5-flashTriggered by @johnny

    sequences containing the digit '7' followed by high activations, possibly indicating a focus on specific numerical patterns or data entries where '7' is prevalent or significant.

    oai_token-act-pair · gpt-4-turboTriggered by @johnny

    hexadecimal numbers, particularly those starting with "0x" followed by a single digit.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @johnny
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.46
     Савезне
    -1.15
    LookAnd
    -1.00
     snippetHide
    -0.94
     doubtnut
    -0.90
    ^(@)
    -0.89
     يتيمه
    -0.89
     bezeichneter
    -0.89
    olesale
    -0.86
    Amicalement
    -0.86
    POSITIVE LOGITS
     “
    0.65
    ↵↵
    0.63
    a
    0.61
    <b>
    0.59
    “
    0.58
     „
    0.57
    <i>
    0.56
     "
    0.55
    <eos>
    0.54
    das
    0.53
    Activations Density 0.328%

    No Known Activations