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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9902
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of quantity or measurement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yelitis
    -0.65
     맞
    -0.61
     nargin
    -0.56
     Fin
    -0.53
     imageNamed
    -0.52
    nador
    -0.50
    stalt
    -0.50
    도록
    -0.49
    guardo
    -0.48
     "");
    
    -0.48
    POSITIVE LOGITS
    aarrggbb
    0.74
    UnusedPrivate
    0.71
    ंदीखरीदारी
    0.68
     erop
    0.59
     estekak
    0.58
     initComponents
    0.57
     Wikimedijinoj
    0.56
    ISCO
    0.56
    MigrationBuilder
    0.56
     himo
    0.55
    Activations Density 0.183%

    No Known Activations