© 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. 31-GEMMASCOPE-RES-16K
    11. 8805
    Prev
    Next
    INDEX
    Explanations

    numerical data or values associated with lists or arrays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numeric digits and numbers appearing in technical code and mathematical expressions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.51
    CloseOperation
    -0.47
    
    -0.46
    AlterField
    -0.46
    |[]
    -0.44
    ѝ
    -0.44
    近
    -0.44
    ＜
    -0.43
    　“
    -0.43
    
    -0.42
    POSITIVE LOGITS
     avoient
    0.41
     utafitiHapana
    0.41
    msgTypes
    0.40
    addCriterion
    0.39
     AssemblyVersion
    0.38
     oprot
    0.35
     nakalista
    0.35
     stră
    0.35
     ब्रेकडाउन
    0.35
    chtest
    0.34
    Activations Density 0.647%

    No Known Activations