© 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. 16-GEMMASCOPE-RES-16K
    11. 15231
    Prev
    Next
    INDEX
    Explanations

    specific nouns and adjectives related to construction and architecture

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

    Follows names or descriptions of events

    np_acts-logits-general · gemini-2.0-flash

    incident or issue

    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
    tagHelperRunner
    -0.98
    帖最后由
    -0.79
     كومونز
    -0.69
     démocratie
    -0.69
     ainfi
    -0.66
     CreateTagHelper
    -0.66
    RenderAtEndOf
    -0.65
    Personensuche
    -0.61
     automatiques
    -0.61
     cesse
    -0.61
    POSITIVE LOGITS
     issue
    0.65
     incident
    0.63
     aspect
    0.62
     deal
    0.60
     situation
    0.59
     idea
    0.58
     thing
    0.58
     fiasco
    0.57
     episode
    0.57
     scenario
    0.56
    Activations Density 0.611%

    No Known Activations