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. 4-GEMMASCOPE-RES-16K
    6. 10940
    Prev
    Next
    INDEX
    Explanations

    terms related to nuclear processes and proteins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.57
    AnchorStyles
    -0.54
    SharedCtor
    -0.53
     StatefulWidget
    -0.53
    MarshalTo
    -0.53
    ⓧ
    -0.53
    رشف
    -0.52
     Fun
    -0.52
    styleType
    -0.51
    gameserver
    -0.49
    POSITIVE LOGITS
     Italijanski
    0.69
    Nuclear
    0.65
     Église
    0.63
     nucléaire
    0.60
    nuclear
    0.58
     Nucl
    0.58
     ſhall
    0.57
    EndTag
    0.56
     nuclear
    0.56
    multicolumn
    0.55
    Activations Density 2.103%

    No Known Activations