© 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. 18-GEMMASCOPE-RES-16K
    11. 3536
    Prev
    Next
    INDEX
    Explanations

    statements of opinion and subjective reflections

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

    Following introductory phrases

    np_acts-logits-general · gemini-2.0-flash

    general knowledge or factual statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -1.02
     виправивши
    -0.81
     purpoſe
    -0.78
     Theſe
    -0.76
    RenderAtEndOf
    -0.75
    StoryboardSegue
    -0.75
    ագրություններ
    -0.74
     fevere
    -0.74
     houſe
    -0.73
    IntoConstraints
    -0.72
    POSITIVE LOGITS
    ,
    0.65
     always
    0.50
    że
    0.50
     also
    0.48
     assai
    0.44
     still
    0.44
     is
    0.43
     could
    0.43
     would
    0.42
    EndContext
    0.42
    Activations Density 0.495%

    No Known Activations