© 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. 10-GEMMASCOPE-RES-16K
    6. 15544
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations of superiority or inferiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.59
    AndEndTag
    -0.56
     незавершена
    -0.48
     dere
    -0.44
    地说道
    -0.42
    (!__
    -0.41
    parsedMessage
    -0.40
    dere
    -0.39
    sers
    -0.39
    transQ
    -0.39
    POSITIVE LOGITS
     superior
    0.94
    superior
    0.82
     SUPERIOR
    0.77
    Superior
    0.77
     Superior
    0.76
     Worse
    0.75
    Worse
    0.73
     worse
    0.71
    better
    0.71
     Better
    0.70
    Activations Density 0.825%

    No Known Activations