© 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. 18-GEMMASCOPE-RES-16K
    11. 3964
    Prev
    Next
    INDEX
    Explanations

    instances of classification and categorization of various types and groups

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

    Types, groups, classes, categories, subtypes

    np_acts-logits-general · gemini-2.0-flash

    classifying things into types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mappedBy
    -0.81
     betweenstory
    -0.78
    InitVars
    -0.67
     TAMBIÉN
    -0.63
    GEBURTS
    -0.63
    帖最后由
    -0.61
     unharmed
    -0.60
    SequentialGroup
    -0.59
    Hochspringen
    -0.58
     Numerade
    -0.57
    POSITIVE LOGITS
     namely
    0.63
     possible
    0.62
     depending
    0.60
     distinguished
    0.58
    :
    0.55
     possibles
    0.54
     posibles
    0.52
    :(
    0.52
     types
    0.50
     iaitu
    0.49
    Activations Density 0.372%

    No Known Activations