© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 50375
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "super"

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

    super followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.39
     golfe
    -0.33
     Rumuni
    -0.32
    NSS
    -0.32
    💲
    -0.31
     algorit
    -0.30
     ailleurs
    -0.30
     Einfluß
    -0.30
     ecosistema
    -0.30
    客様
    -0.29
    POSITIVE LOGITS
    super
    2.98
     super
    2.70
    Super
    2.31
     Super
    2.17
     SUPER
    2.05
    SUPER
    1.96
     супер
    1.86
    超级
    1.67
    スーパー
    1.59
    Супер
    1.59
    Activations Density 0.003%

    No Known Activations