© 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. 27-GEMMASCOPE-RES-16K
    11. 9286
    Prev
    Next
    INDEX
    Explanations

    themes of change and transformation in life situations

    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
    MigrationBuilder
    -0.54
    principalColumn
    -0.52
    ftagPool
    -0.45
    DockStyle
    -0.45
    '}>
    -0.41
     Gaulle
    -0.41
     gern
    -0.40
    Trin
    -0.40
     rege
    -0.40
     JAXB
    -0.39
    POSITIVE LOGITS
     when
    0.87
     כאשר
    0.65
     زمانی
    0.65
    when
    0.65
     когда
    0.64
     quando
    0.61
     όταν
    0.59
     kiedy
    0.58
     जब
    0.58
     když
    0.58
    Activations Density 0.343%

    No Known Activations