© 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. 11423
    Prev
    Next
    INDEX
    Explanations

    the presence of specific markers or indicators of structured documents, likely related to technical or scientific contexts

    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
     WebDriverWait
    -0.60
     and
    -0.60
     ControllerBase
    -0.57
    Organisateur
    -0.57
     (
    -0.56
    DebuggerNonUser
    -0.56
     AspNetCore
    -0.55
    apimachinery
    -0.55
    DoubleQuotes
    -0.54
     FormsModule
    -0.52
    POSITIVE LOGITS
     houſe
    0.97
     pleaſure
    0.96
     purpoſe
    0.95
     ſtate
    0.91
     myſelf
    0.91
     anſ
    0.89
     uſe
    0.87
     Houſe
    0.86
     Majefty
    0.86
     Monfieur
    0.85
    Activations Density 0.033%

    No Known Activations