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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2401
    Prev
    Next
    INDEX
    Explanations

    configuration settings and options related to web technologies and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Values assigned with equals signs

    np_acts-logits-general · gemini-2.0-flash

    attribute values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ytterligare
    -0.56
    VersionUID
    -0.50
    figsize
    -0.48
    MetaType
    -0.48
    boni
    -0.47
    他又
    -0.47
    mapStateToProps
    -0.46
    phous
    -0.44
    FieldBuilder
    -0.44
     surla
    -0.44
    POSITIVE LOGITS
     none
    0.85
     onCreateView
    0.80
     <<<<<<<<<<<<<<
    0.76
     None
    0.74
    none
    0.74
     always
    0.72
     never
    0.72
     Nunca
    0.65
    awsze
    0.65
     Never
    0.65
    Activations Density 0.400%

    No Known Activations