Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7699
    Prev
    Next
    INDEX
    Explanations

    specific institutions and locations related to research and education

    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
     ModelExpression
    -0.36
    #+#
    -0.35
     (;;
    -0.31
     Taktlose
    -0.31
    undheit
    -0.31
     transfieras
    -0.31
    ษ
    -0.31
    
    -0.31
    üf
    -0.30
    UIControlState
    -0.30
    POSITIVE LOGITS
     inst
    2.70
     Inst
    2.67
     instance
    2.59
     Instance
    2.56
     INST
    2.56
    instance
    2.55
    Inst
    2.53
     institute
    2.52
    inst
    2.48
    Instance
    2.45
    Activations Density 0.884%

    No Known Activations