© 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. 10-GEMMASCOPE-RES-16K
    11. 7154
    Prev
    Next
    INDEX
    Explanations

    references to list lengths and sizes

    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
    adaptiveStyles
    -0.55
    awtextra
    -0.53
    цездатний
    -0.48
     NavController
    -0.46
    ProcessEvent
    -0.43
    djangoproject
    -0.40
     diagnos
    -0.40
    يميديا
    -0.40
    expandindo
    -0.40
     ModelExpression
    -0.40
    POSITIVE LOGITS
    length
    1.20
     length
    1.01
    Length
    0.95
    size
    0.90
    LENGTH
    0.84
     Length
    0.82
     LENGTH
    0.78
    isNotEmpty
    0.75
     size
    0.74
    Size
    0.71
    Activations Density 0.227%

    No Known Activations