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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7555
    Prev
    Next
    INDEX
    Explanations

    specific proteins and genes associated with biological research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cæ
    -0.52
     ſta
    -0.49
     ſte
    -0.47
     ſmall
    -0.44
     ſt
    -0.43
     occaf
    -0.41
     loue
    -0.41
     pleaſure
    -0.41
     ſtand
    -0.41
     houſe
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.81
     gambe
    0.81
    ftagPool
    0.79
     spp
    0.75
     Species
    0.74
    ReusableCell
    0.71
    
    0.71
     species
    0.70
     sp
    0.69
    [@BOS@]
    0.69
    Activations Density 0.335%

    No Known Activations