Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 10175
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to principles and notions of justice and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.52
    astify
    -0.48
    省市镇
    -0.47
    LastError
    -0.45
     '{@
    -0.45
    AdapterView
    -0.44
     @"/
    -0.44
    Diwedd
    -0.43
     אומר
    -0.43
    SdkVersion
    -0.43
    POSITIVE LOGITS
    :+:
    0.63
     ModelExpression
    0.63
     estekak
    0.61
    Alike
    0.59
     CURIAM
    0.59
    carry
    0.59
    usercontent
    0.58
     Pristupljeno
    0.57
    UnknownFieldSet
    0.56
     مصرى
    0.56
    Activations Density 0.414%

    No Known Activations