© 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. 8975
    Prev
    Next
    INDEX
    Explanations

    terms related to methods and techniques in scientific research

    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
     soigneusement
    -0.34
     TextAppearance
    -0.34
    /******/
    -0.32
     känna
    -0.32
     hjälp
    -0.32
    maphore
    -0.31
    ougou
    -0.30
    bundes
    -0.30
    HasBeenSet
    -0.30
     برانيه
    -0.30
    POSITIVE LOGITS
     suitable
    2.56
    suitable
    2.31
     suited
    2.20
    Suitable
    2.16
     Suitable
    2.16
     suitability
    2.02
     appropriate
    1.98
    suited
    1.95
     unsuitable
    1.85
     ideal
    1.80
    Activations Density 0.808%

    No Known Activations