© 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. 21-GEMMASCOPE-RES-16K
    6. 2683
    Prev
    Next
    INDEX
    Explanations

    phrases related to participation and experience in a study or research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.53
     löytyy
    -0.49
     crescere
    -0.47
     valmist
    -0.46
    hésite
    -0.45
    LayoutPanel
    -0.45
     afecta
    -0.44
     الحره
    -0.44
     afectan
    -0.43
    grao
    -0.42
    POSITIVE LOGITS
    Portale
    0.47
    endfor
    0.44
     himo
    0.41
    تقاوى
    0.41
    enderror
    0.40
     ErrIntOverflow
    0.40
     beruf
    0.40
    gk
    0.39
     campus
    0.39
    Kjelder
    0.39
    Activations Density 0.372%

    No Known Activations