© 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. 23-GEMMASCOPE-RES-16K
    11. 9124
    Prev
    Next
    INDEX
    Explanations

    sentences that aim to provide insight or clarification on complex topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.81
     nakalista
    -0.71
     estekak
    -0.71
     الرياضيه
    -0.69
    +#+#
    -0.68
     مرئيه
    -0.67
     dAtA
    -0.67
     ModelExpression
    -0.65
    msgTypes
    -0.63
     للمعارف
    -0.61
    POSITIVE LOGITS
    少しでも
    0.41
     möglichst
    0.40
     promote
    0.36
     mümkün
    0.33
    尽可能
    0.33
    できるだけ
    0.33
     ease
    0.32
     convenience
    0.32
     facilitate
    0.30
     hopefully
    0.30
    Activations Density 0.481%

    No Known Activations