© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13782
    Prev
    Next
    INDEX
    Explanations

    direct quotes from individuals in various professional roles

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

    Follows titles or roles

    np_acts-logits-general · gemini-2.0-flash

    people with titles or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ніципалі
    -0.64
     betweenstory
    -0.50
     yym
    -0.50
    inel
    -0.50
    SharedDtor
    -0.50
     invokingState
    -0.50
     zwiſchen
    -0.50
    ꜣ
    -0.49
     müſſen
    -0.49
    expandindo
    -0.49
    POSITIVE LOGITS
     CEO
    0.40
     NavController
    0.38
    脚注の使い方
    0.37
     ontvang
    0.35
    CEO
    0.35
     President
    0.34
    énieurs
    0.34
     president
    0.34
     reflected
    0.34
     stated
    0.33
    Activations Density 0.030%

    No Known Activations