© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 7517
    Prev
    Next
    INDEX
    Explanations

    terms and parameters related to options and requests in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.70
    expandindo
    -0.68
     Мексичка
    -0.61
     JpaRepository
    -0.59
    TagMode
    -0.58
     Pingback
    -0.56
     DPRD
    -0.53
    sproble
    -0.51
    HomeAsUpEnabled
    -0.51
     typeof
    -0.49
    POSITIVE LOGITS
     <>",
    0.69
    ModelAttribute
    0.60
    Request
    0.59
    CreateInfo
    0.57
    lapsingToolbar
    0.56
    RetentionPolicy
    0.56
    RuleContext
    0.55
    GridData
    0.55
    RequestOptions
    0.53
    ARGS
    0.52
    Activations Density 0.222%

    No Known Activations