© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 14721
    Prev
    Next
    INDEX
    Explanations

    references to secrets and secretive elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.98
     становника
    -0.94
    NameInMap
    -0.94
     GetEnumerator
    -0.84
    racite
    -0.76
    addPreferredGap
    -0.76
    OGND
    -0.76
    PyExc
    -0.73
     виправивши
    -0.72
    harusnya
    -0.71
    POSITIVE LOGITS
     secret
    2.48
     Secret
    2.39
    Secret
    2.37
    secret
    2.28
     SECRET
    2.20
     secrets
    2.15
     Secrets
    1.92
    SECRET
    1.80
    Secrets
    1.79
    secrets
    1.77
    Activations Density 0.088%

    No Known Activations