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. 22-GEMMASCOPE-RES-16K
    6. 10306
    Prev
    Next
    INDEX
    Explanations

    evidence related to sentencing and legal rulings

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

    Code or markup delimiters

    np_acts-logits-general · gemini-2.0-flash

    prepositions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reaſon
    -0.81
     Monfieur
    -0.78
     initComponents
    -0.78
     utafitiHapana
    -0.78
    )");
    
    -0.78
     ſmall
    -0.78
    Carriera
    -0.76
     Efq
    -0.75
     purpoſe
    -0.73
    ++
    
    -0.72
    POSITIVE LOGITS
    and
    1.00
    with
    0.97
    from
    0.82
    in
    0.81
     with
    0.79
    for
    0.78
    of
    0.74
     and
    0.74
     in
    0.74
    which
    0.74
    Activations Density 0.854%

    No Known Activations