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. 7-GEMMASCOPE-RES-16K
    6. 6118
    Prev
    Next
    INDEX
    Explanations

    various forms of indentation and formatting in code or text structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.82
    DoubleQuotes
    -0.79
    ScopeManager
    -0.76
    AndEndTag
    -0.70
    endphp
    -0.68
     كومونز
    -0.67
     فريبيس
    -0.66
    FunctionFlags
    -0.65
    Clik
    -0.64
     fes
    -0.61
    POSITIVE LOGITS
    :✨
    0.53
    getDescriptor
    0.47
     Na
    0.45
    EXTERN
    0.43
     yarış
    0.42
     art
    0.42
     zwar
    0.41
    arbox
    0.41
    Na
    0.41
    Literatur
    0.40
    Activations Density 0.232%

    No Known Activations