© 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. 9277
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to cooking and scientific contexts

    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
     limited
    -0.31
     three
    -0.31
    verhältnisse
    -0.31
     sur
    -0.30
    SupportActionBar
    -0.29
    ambu
    -0.29
     step
    -0.29
    меты
    -0.29
     follow
    -0.29
     обра
    -0.29
    POSITIVE LOGITS
    Diweddarwch
    0.78
    principalTable
    0.76
     kasarigan
    0.69
    ftagPool
    0.66
    awtextra
    0.66
    OGND
    0.64
     transfieras
    0.63
     للاسماء
    0.63
    posedge
    0.60
    SerializedSize
    0.59
    Activations Density 0.401%

    No Known Activations