© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8072
    Prev
    Next
    INDEX
    Explanations

    common phrases related to generalizations or summaries about situations or conditions

    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
    onent
    -0.42
    eluarkan
    -0.40
    WithIdentifier
    -0.39
     Campe
    -0.38
     Dulles
    -0.38
     dangere
    -0.37
    ionales
    -0.37
    adaptiveStyles
    -0.37
    acheco
    -0.36
     Swann
    -0.36
    POSITIVE LOGITS
     flesta
    0.85
     kebanyakan
    0.84
     maioria
    0.80
     majority
    0.79
     meisten
    0.76
     plupart
    0.75
     mostly
    0.73
     Mostly
    0.71
    Mostly
    0.71
     meeste
    0.71
    Activations Density 0.390%

    No Known Activations