© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    terms related to voter registration and integrity issues

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

    Registration or recording information

    np_acts-logits-general · gemini-2.0-flash

    official registration and records

    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
    argout
    -0.63
    ontale
    -0.53
    tableFuture
    -0.53
    aptation
    -0.50
    ispiel
    -0.49
    VIATIONS
    -0.47
     ब्रेकडाउन
    -0.47
     تضيفلها
    -0.46
     Drapeau
    -0.45
    ControllerTest
    -0.45
    POSITIVE LOGITS
     register
    1.75
     registers
    1.66
     Register
    1.58
     records
    1.54
     registry
    1.52
     registered
    1.52
     registration
    1.49
     regist
    1.45
     Registers
    1.43
     registering
    1.40
    Activations Density 0.415%

    No Known Activations