© 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. 20-GEMMASCOPE-RES-65K
    6. 618
    Prev
    Next
    INDEX
    Explanations

    phrases related to the future of economic and political stability

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

    phrases related to future predictions or consequences

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

    futurewise statements

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AxisAlignment
    -0.82
    esModule
    -0.69
    bootstrapcdn
    -0.69
    kloped
    -0.66
     EdgeInsets
    -0.66
    EndContext
    -0.65
    addCriterion
    -0.63
    Портал
    -0.62
    clerview
    -0.60
     Moines
    -0.57
    POSITIVE LOGITS
    ↵↵
    0.89
    <eos>
    0.86
     Also
    0.69
     همچنین
    0.66
    Also
    0.64
    XmlEnum
    0.58
    ValueStyle
    0.56
     ayrıca
    0.55
    also
    0.55
     avoient
    0.54
    Activations Density 0.132%

    No Known Activations