© 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. 22-GEMMASCOPE-RES-16K
    6. 15355
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structures in programming

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

    "resist" or "promote"

    np_acts-logits-general · gemini-2.0-flash

    resistin effects and expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.62
     Pristupljeno
    -0.55
    ArgsConstructor
    -0.54
     exportation
    -0.54
    #+#
    -0.53
    deletion
    -0.52
    RetentionPolicy
    -0.52
    ApplicationTests
    -0.52
     Deletion
    -0.51
    WebControls
    -0.50
    POSITIVE LOGITS
     Evolve
    0.86
     Navigate
    0.83
    ULATE
    0.82
     Educate
    0.81
    atize
    0.79
     Migrate
    0.78
     Marry
    0.78
     Optimize
    0.75
    OLVE
    0.75
    itize
    0.74
    Activations Density 0.498%

    No Known Activations