© 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. 8862
    Prev
    Next
    INDEX
    Explanations

    words indicating studies, findings, or evidence related to scientific research

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

    a point in time

    np_acts-logits-general · gemini-2.0-flash

    up to date or so far

    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
    Gambas
    -0.68
    DebuggerNonUser
    -0.67
     protoimpl
    -0.66
     gql
    -0.64
    !")
    -0.63
     ISNI
    -0.63
    Становништво
    -0.63
     betweenstory
    -0.62
     ProtoMessage
    -0.62
     typelib
    -0.61
    POSITIVE LOGITS
     bisher
    1.84
     bislang
    1.66
     hitherto
    1.43
     sejauh
    1.39
     yet
    1.38
     till
    1.25
     bisherigen
    1.25
    迄
    1.18
    至今
    1.16
     until
    1.16
    Activations Density 0.583%

    No Known Activations