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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6923
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions, requirements, or characteristics associated with services or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manfaat
    -0.40
    tonode
    -0.38
    aksana
    -0.37
     käytet
    -0.37
    tudo
    -0.36
     verk
    -0.36
    保険
    -0.36
     argint
    -0.35
     acest
    -0.35
    Pranala
    -0.35
    POSITIVE LOGITS
    Jeografia
    0.61
    oredCriteria
    0.59
     ProtoMessage
    0.51
    utives
    0.46
    ArrowToggle
    0.44
     OMITBAD
    0.44
    MigrationBuilder
    0.44
    oa̍t
    0.43
    EndProject
    0.43
     Италијани
    0.42
    Activations Density 0.524%

    No Known Activations