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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3108
    Prev
    Next
    INDEX
    Explanations

    assignments and initializations in code

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

    C-like syntax and expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical formulas and code snippets

    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
    (((
    -0.97
     ((
    -0.77
    ((
    -0.75
    =((
    -0.72
    )((
    -0.65
     (((
    -0.64
    WritableDatabase
    -0.60
    ((((
    -0.59
    )(((
    -0.57
     (($
    -0.57
    POSITIVE LOGITS
    Havolalar
    0.57
     }}}{
    0.55
    "}";
    0.54
    ']):
    0.53
    MLLoader
    0.52
    "]=
    0.52
    ")]
    
    0.51
    "]="
    0.47
    ]={
    0.47
    REQUIRES
    0.47
    Activations Density 0.319%

    No Known Activations