© 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. 38-GEMMASCOPE-RES-16K
    11. 8379
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation and directional guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.46
    archiviato
    -0.38
     CanadaChoose
    -0.35
    InstrumentedTest
    -0.35
     incomplète
    -0.35
    LElement
    -0.35
    éramos
    -0.34
    الدراسه
    -0.34
    AutoScaleMode
    -0.33
    ynb
    -0.32
    POSITIVE LOGITS
     ahead
    3.70
     Ahead
    3.08
    ahead
    2.97
    Ahead
    2.89
     AHEAD
    2.78
    переди
    1.35
     delante
    1.23
     devant
    1.20
     voraus
    1.12
     вперед
    1.11
    Activations Density 0.371%

    No Known Activations