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. 25-GEMMASCOPE-RES-16K
    6. 4196
    Prev
    Next
    INDEX
    Explanations

    methods related to object properties and handling collections in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.74
    !.
    -0.64
    .
    
    -0.60
    MigrationBuilder
    -0.60
    errHandler
    -0.58
     ?.
    -0.58
     $.
    -0.57
     betweenstory
    -0.56
    !».
    -0.56
    ?.
    -0.56
    POSITIVE LOGITS
    ()
    0.85
    ()+
    0.62
    ()>
    0.60
    PRNewswire
    0.60
    ()*
    0.58
    ()-
    0.58
    ()<<
    0.57
     ModelExpression
    0.55
    rungsseite
    0.55
    ()==
    0.53
    Activations Density 0.168%

    No Known Activations