© 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. 23-GEMMASCOPE-RES-16K
    6. 6548
    Prev
    Next
    INDEX
    Explanations

    items related to programming tags or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geschiedenis
    -0.53
     nền
    -0.53
     five
    -0.50
     وتسجيلات
    -0.47
     Five
    -0.47
    five
    -0.47
     Ng
    -0.46
     FIVE
    -0.46
     item
    -0.44
     Zak
    -0.43
    POSITIVE LOGITS
    public
    1.85
     public
    1.52
    Public
    1.15
     Public
    1.13
     pubblici
    1.12
     PUBLIC
    1.08
     Pública
    1.04
    PUBLIC
    1.03
     público
    0.98
     pública
    0.96
    Activations Density 0.022%

    No Known Activations