© 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. 1754
    Prev
    Next
    INDEX
    Explanations

    words that relate to completion or endings

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

    ending, completing, or finalizing something

    np_acts-logits-general · gemini-2.0-flash

    finishing or finished actions

    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
     gyhoeddwyd
    -0.75
    rungsseite
    -0.74
    TagMode
    -0.69
    OrNil
    -0.67
    лтамалар
    -0.64
     Anfitrión
    -0.60
     Moors
    -0.59
    LEncoder
    -0.57
    MigrationBuilder
    -0.56
     мәкалә
    -0.55
    POSITIVE LOGITS
     FINISH
    0.81
     unfinished
    0.78
    unfinished
    0.73
     touches
    0.73
     Finish
    0.71
     Fino
    0.69
    FINISH
    0.67
     TOUCH
    0.67
     finish
    0.66
    Unfinished
    0.65
    Activations Density 0.085%

    No Known Activations