© 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. 1629
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and database queries

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

    Filtering and searching

    np_acts-logits-general · gemini-2.0-flash

    filter and search criteria

    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
     nahilalakip
    -0.83
    脚注の使い方
    -0.62
     виправивши
    -0.58
     CreateTagHelper
    -0.54
    ंदीखरीदारी
    -0.53
    oplast
    -0.52
    ronpa
    -0.52
    enumi
    -0.52
    complexType
    -0.51
    MLLoader
    -0.51
    POSITIVE LOGITS
     filter
    1.67
     filters
    1.62
     Filter
    1.54
     filtering
    1.47
     Filters
    1.45
    Filter
    1.44
    filter
    1.39
     filtre
    1.35
     filtro
    1.30
     filtered
    1.29
    Activations Density 0.368%

    No Known Activations