Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9153
    Prev
    Next
    INDEX
    Explanations

    rules and guidelines related to professional conduct and etiquette

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

    rules, policies, and norms

    np_acts-logits-general · gemini-2.0-flash

    rules and norms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.73
    ArgsConstructor
    -0.71
    WithIOException
    -0.71
    JsonHelper
    -0.63
    новниш
    -0.60
     disambiguazione
    -0.60
    thâu
    -0.59
    ActionCreators
    -0.59
     NSCoder
    -0.58
     AssemblyCulture
    -0.57
    POSITIVE LOGITS
     rules
    1.42
     Rules
    1.23
     rule
    1.22
    rules
    1.20
    Rules
    1.19
     RULES
    1.13
     regels
    1.09
     guidelines
    1.06
    rule
    1.03
     regulations
    1.03
    Activations Density 0.488%

    No Known Activations