Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12815
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or realization, especially those starting with "Oh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasKey
    -0.46
    Évaluation
    -0.45
    SuppressMessage
    -0.44
    BindingResult
    -0.43
     HasFactory
    -0.42
     surla
    -0.41
    ModelBuilder
    -0.40
     Италијани
    -0.40
    elt
    -0.40
     evaluation
    -0.40
    POSITIVE LOGITS
     Oh
    0.91
     oh
    0.89
    Oh
    0.84
    Oooh
    0.68
    Ohhhh
    0.65
    Ohhh
    0.64
     OH
    0.63
    GEBURTSDATUM
    0.56
    Ах
    0.56
    oh
    0.55
    Activations Density 0.086%

    No Known Activations