© 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. 451
    Prev
    Next
    INDEX
    Explanations

    structured data formats and definitions related to configuration and settings

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

    Code, paths, or keys in dictionaries

    np_acts-logits-general · gemini-2.0-flash

    programmatic access and identifiers

    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
    onAttach
    -0.68
    BorderFactory
    -0.57
    RetentionPolicy
    -0.56
     majors
    -0.56
    InvalidProtocol
    -0.56
    TintMode
    -0.55
    FilterChain
    -0.55
    <?
    -0.54
     Majors
    -0.53
    ReusableCell
    -0.52
    POSITIVE LOGITS
    NameInMap
    0.63
    ⓘ
    0.57
     renseignements
    0.55
     démocr
    0.50
    Swagger
    0.49
    uxxxx
    0.49
    èce
    0.48
    IndentedString
    0.48
     localVar
    0.47
    jęt
    0.47
    Activations Density 0.293%

    No Known Activations