© 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. 37-GEMMASCOPE-RES-16K
    6. 5418
    Prev
    Next
    INDEX
    Explanations

    geographical locations related to a person's biography in the context of sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shenandoah
    -0.40
    tomy
    -0.37
    🖕
    -0.35
     transformer
    -0.34
     Paige
    -0.34
     equivalence
    -0.33
    iettivo
    -0.33
    stretched
    -0.32
     Lush
    -0.32
    pedia
    -0.32
    POSITIVE LOGITS
    liceerd
    0.58
     Tobago
    0.58
     Trinidad
    0.57
     Trin
    0.57
     trin
    0.54
     виправивши
    0.53
    fromnode
    0.52
    __":
    
    0.51
     IFTT
    0.51
     TT
    0.51
    Activations Density 0.238%

    No Known Activations