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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11927
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to analysis, assessment, and variables in the context of studies or research

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

    References or citations (e.g., "see ... at")

    np_acts-logits-general · gemini-2.0-flash

    legal citations referencing above

    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
    MessageOf
    -0.55
    RuleContext
    -0.53
     disponibilités
    -0.51
     cucchiaio
    -0.49
    kini
    -0.49
    tetur
    -0.48
    jati
    -0.48
    xa
    -0.47
    Données
    -0.47
    ENIA
    -0.47
    POSITIVE LOGITS
     mentioned
    1.76
     above
    1.61
     aforementioned
    1.61
    mentioned
    1.49
    above
    1.41
     aforesaid
    1.39
     described
    1.32
     Mentioned
    1.30
    上述
    1.25
     mencionado
    1.22
    Activations Density 1.000%

    No Known Activations