© 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. 18-GEMMASCOPE-RES-16K
    11. 53
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax related to object and list handling in programming

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

    Java type conversions and casting

    np_acts-logits-general · gemini-2.0-flash

    casting and returns

    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
    AndEndTag
    -0.88
    IUrlHelper
    -0.59
    RegressionTest
    -0.57
    IsContent
    -0.54
    prefixer
    -0.54
     mijne
    -0.53
    ppuden
    -0.53
     trúc
    -0.52
    stateProvider
    -0.51
    randomUUID
    -0.51
    POSITIVE LOGITS
    ((
    1.24
     ((
    1.21
     *((
    1.08
    >((
    0.99
    (((
    0.92
    cast
    0.91
    ",(
    0.90
     cast
    0.89
    *((
    0.86
    =(
    0.84
    Activations Density 0.198%

    No Known Activations