© 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-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 7969
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to appearance and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     možnost
    -0.41
     możliwość
    -0.39
    PullParser
    -0.36
     kerana
    -0.35
     method
    -0.35
     fêtes
    -0.34
     guerrero
    -0.34
     prêtres
    -0.34
     isNameExpr
    -0.34
     przedsiębior
    -0.33
    POSITIVE LOGITS
     sounded
    0.66
    looks
    0.60
    seemed
    0.58
     propOrder
    0.58
     LOOKS
    0.58
    Looks
    0.57
    feels
    0.57
    Feels
    0.57
    Parece
    0.56
     resemble
    0.56
    Activations Density 0.078%

    No Known Activations