© 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. 27-GEMMASCOPE-RES-16K
    6. 9262
    Prev
    Next
    INDEX
    Explanations

    references to structured data formats and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.76
     مرئيه
    -0.66
     <=",
    -0.58
    rungsseite
    -0.58
     JpaRepository
    -0.55
    RegistryLite
    -0.55
    AutoScaleMode
    -0.54
    ьаж
    -0.52
    optionalTypeArgs
    -0.48
    Искәрмәләр
    -0.47
    POSITIVE LOGITS
    ]-[
    0.40
     STANDARD
    0.38
    ][
    0.38
    ]
    0.38
     [
    0.37
    ceau
    0.36
    FontOfSize
    0.36
    ].
    0.36
     Bas
    0.35
    责编
    0.35
    Activations Density 1.587%

    No Known Activations