© 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. 33-GEMMASCOPE-RES-16K
    11. 8234
    Prev
    Next
    INDEX
    Explanations

    content related to research methodology and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.56
     HasFactory
    -0.56
    medriver
    -0.50
    principalColumn
    -0.49
    
    -0.49
    homonymie
    -0.49
     vectorielle
    -0.48
     AspNetCore
    -0.48
    gemeente
    -0.48
    FilterChain
    -0.47
    POSITIVE LOGITS
     qualitative
    1.27
     Qualitative
    1.02
     interviews
    0.96
    Qualitative
    0.96
     interview
    0.88
    Interviews
    0.85
     Interviews
    0.84
     qualit
    0.82
     qualitatively
    0.81
     ethnographic
    0.79
    Activations Density 0.773%

    No Known Activations