© 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. 9918
    Prev
    Next
    INDEX
    Explanations

    terms related to qualitative analysis and evaluation

    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
    webElementGuid
    -0.63
     vettor
    -0.63
     therefor
    -0.62
     Unidas
    -0.61
     Pozna
    -0.60
    ^(@)
    -0.60
    mitian
    -0.59
     Jez
    -0.59
     geologic
    -0.58
    createServer
    -0.58
    POSITIVE LOGITS
    quote
    0.84
     idea
    0.78
     objective
    0.75
     Quanti
    0.73
     quantify
    0.73
     mergeFrom
    0.71
     Idea
    0.68
    idea
    0.68
    quantitative
    0.68
    Idea
    0.67
    Activations Density 0.113%

    No Known Activations