Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1124
    Prev
    Next
    INDEX
    Explanations

    specific numeric data points or references in the text

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

    Time stamps after a date

    np_acts-logits-general · gemini-2.0-flash

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.75
    PrototypeOf
    -0.67
     OFDb
    -0.67
     resourceCulture
    -0.64
     referrerpolicy
    -0.61
    таратура
    -0.61
     comuniques
    -0.61
     szóci
    -0.61
    <bos>
    -0.61
    ########.
    -0.59
    POSITIVE LOGITS
    iggio
    0.61
     $_"
    0.60
    issauga
    0.56
    thodon
    0.56
     glancing
    0.54
     Typing
    0.53
     typing
    0.53
    9
    0.53
     glan
    0.52
     swans
    0.52
    Activations Density 0.106%

    No Known Activations