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. 17-GEMMASCOPE-RES-16K
    6. 13137
    Prev
    Next
    INDEX
    Explanations

    reviews and comments about specific products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.62
     
    -0.59
     (
    -0.53
     "
    -0.53
     tzw
    -0.46
    かわ
    -0.46
     one
    -0.45
     конце
    -0.45
     „
    -0.44
    mayer
    -0.43
    POSITIVE LOGITS
     Majefty
    1.09
    脚注の使い方
    1.08
    новништво
    1.08
     autorytatywna
    1.06
    RenderAtEndOf
    1.06
    posedge
    1.02
    دانشنامهٔ
    0.99
     Normdatei
    0.97
     Walkover
    0.97
     AssemblyCulture
    0.95
    Activations Density 0.216%

    No Known Activations