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. 3-GEMMASCOPE-RES-16K
    6. 8233
    Prev
    Next
    INDEX
    Explanations

    specific structural elements or terms related to code and programming syntax

    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
    </i>
    -0.56
    awtextra
    -0.52
    してお
    -0.52
     melting
    -0.51
    z
    -0.51
    r
    -0.50
    לא
    -0.50
     odds
    -0.49
    oneofs
    -0.48
     quim
    -0.48
    POSITIVE LOGITS
    |}{
    3.56
    }{*}{
    2.02
    |}{$
    1.95
    |}{}
    1.55
    |}{\
    1.21
    }{*}{}
    0.96
    :]:
    0.82
    )}]{
    0.82
    )";
    
    0.79
    )\}$
    0.78
    Activations Density 0.134%

    No Known Activations