© 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. 20-GEMMASCOPE-RES-16K
    11. 15420
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between states and territories in legislative or political contexts

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

    Terms related to government locations

    np_acts-logits-general · gemini-2.0-flash

    state and local entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stat
    -1.18
     Stat
    -1.16
    statement
    -1.09
    stat
    -1.07
     statement
    -1.06
     stat
    -1.06
     STAT
    -1.04
    STAT
    -1.03
    Statement
    -1.02
     Stati
    -1.01
    POSITIVE LOGITS
    multer
    0.59
    ագրություններ
    0.59
    owicz
    0.48
    bumptech
    0.43
    MockBean
    0.42
    caz
    0.41
    Bioaccumulative
    0.40
     Arzneimit
    0.40
    anadas
    0.40
    новниш
    0.39
    Activations Density 0.210%

    No Known Activations