© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10034
    Prev
    Next
    INDEX
    Explanations

    references to entities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kloped
    -0.69
     IT
    -0.56
    IT
    -0.47
    さん
    -0.47
     MessageBoxIcon
    -0.47
     (
    -0.46
    <eos>
    -0.46
     j
    -0.45
     axios
    -0.43
    sitis
    -0.43
    POSITIVE LOGITS
     itſelf
    1.31
     ―――――
    1.14
     raiſ
    1.05
     Theſe
    1.02
     myſelf
    0.99
     Houſe
    0.96
     Anſ
    0.95
     Reſ
    0.94
     Efq
    0.94
     ſind
    0.93
    Activations Density 0.044%

    No Known Activations