© 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. 3497
    Prev
    Next
    INDEX
    Explanations

    different types of formal documentation and their associated actions or outcomes

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

    phrases describing events that occurred without violence or opposition.

    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
     initComponents
    -0.80
    rrggbb
    -0.57
    nonatomic
    -0.56
    الحياه
    -0.54
    Autoritní
    -0.50
    AutoScaleMode
    -0.50
     disambiguazione
    -0.50
    terus
    -0.49
    providedIn
    -0.48
    MergeFrom
    -0.47
    POSITIVE LOGITS
     issued
    1.00
     uttered
    0.95
     emitted
    0.94
     delivered
    0.85
     emiti
    0.84
     Issued
    0.82
     performed
    0.82
    issued
    0.76
    Issued
    0.75
     issuing
    0.71
    Activations Density 1.234%

    No Known Activations