© 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. 2924
    Prev
    Next
    INDEX
    Explanations

    connections between contrasting or ambiguous terms and scenarios

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

    Follows "or" or "and", indicating continuation

    np_acts-logits-general · gemini-2.0-flash

    or and etc

    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
    Filmographie
    -0.69
    المشاركات
    -0.64
    parsedMessage
    -0.64
     kasarigan
    -0.61
    DeleteBehavior
    -0.53
    Portail
    -0.52
     VizieR
    -0.52
     дописавши
    -0.50
    Notae
    -0.49
    |}{\
    -0.49
    POSITIVE LOGITS
     whatnot
    2.00
     stuff
    1.93
     such
    1.67
     everything
    1.61
     etc
    1.60
     things
    1.52
    etc
    1.44
     dergleichen
    1.43
     sebagainya
    1.43
    everything
    1.41
    Activations Density 0.206%

    No Known Activations