© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 964
    Prev
    Next
    INDEX
    Explanations

    phrases questioning the applicability or relevance of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rând
    -0.81
    ]--;
    -0.79
     pleaſure
    -0.77
     ſame
    -0.74
    lccccc
    -0.73
     houſe
    -0.73
    BibitemShut
    -0.73
    ^(@)
    -0.72
     Finlay
    -0.72
     uſed
    -0.71
    POSITIVE LOGITS
    SuppressMessage
    0.69
    TypedDataSet
    0.68
     why
    0.67
     HasFactory
    0.60
    MarshalTo
    0.59
    rungsseite
    0.59
    apimachinery
    0.58
    AssignableFrom
    0.58
     LoggerFactory
    0.58
     GenerationType
    0.58
    Activations Density 0.009%

    No Known Activations