© 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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13452
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations typically used in formal proofs or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.85
     חיצוניים
    -0.58
    httphttps
    -0.57
    unknownFields
    -0.57
    󠁴
    -0.56
     мәкал
    -0.55
    bootstrapcdn
    -0.53
    最快更新
    -0.53
     informée
    -0.53
     jsPsych
    -0.53
    POSITIVE LOGITS
     nakalista
    0.68
    ValueStyle
    0.62
    intios
    0.52
     Roskov
    0.47
     arquite
    0.46
    UnusedPrivate
    0.45
    ambién
    0.43
     dieux
    0.42
     conmigo
    0.41
    NSUInteger
    0.40
    Activations Density 3.158%

    No Known Activations