© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    connections related to the brain and its functionalities

    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
    OGND
    -0.57
    sense
    -0.54
    sam
    -0.54
     Италијани
    -0.54
    san
    -0.53
    sag
    -0.53
    sensor
    -0.52
    sin
    -0.52
    sink
    -0.52
    sus
    -0.51
    POSITIVE LOGITS
     ste
    1.26
     sta
    1.21
     STE
    1.05
     स्ट
    1.05
     Ste
    1.05
     Steve
    1.03
     Sta
    1.02
     ST
    1.02
    Sta
    1.02
    ステ
    0.99
    Activations Density 2.432%

    No Known Activations