© 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. 9-GEMMASCOPE-RES-16K
    6. 2615
    Prev
    Next
    INDEX
    Explanations

    aspects of programming code syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.45
     Worldwide
    -0.43
     rest
    -0.43
    igor
    -0.42
     Geh
    -0.41
     worldwide
    -0.39
    rs
    -0.39
    underbrace
    -0.39
     World
    -0.39
     sport
    -0.39
    POSITIVE LOGITS
     BoxDecoration
    0.81
    पया
    0.73
    catraz
    0.70
     internetowa
    0.68
    <bos>
    0.65
     ModelExpression
    0.65
    országban
    0.65
     ALC
    0.64
    struktion
    0.63
    principalTable
    0.63
    Activations Density 0.150%

    No Known Activations