© 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. 595
    Prev
    Next
    INDEX
    Explanations

    references to copyright, permission, and assistance related to content usage

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

    Following "you" or start of turn

    np_acts-logits-general · gemini-2.0-flash

    questions or advice

    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
    GTCX
    -0.38
     öss
    -0.37
    AddTagHelper
    -0.37
    Bek
    -0.35
    enterOuterAlt
    -0.34
    ].)
    -0.34
    ]').
    -0.33
     تک
    -0.32
     причем
    -0.32
    ≦)
    -0.32
    POSITIVE LOGITS
    Personendaten
    0.65
     yourself
    0.57
     EconPapers
    0.52
     concerns
    0.51
     étoit
    0.49
    rictions
    0.48
    yourself
    0.48
    Gambas
    0.48
     Савезне
    0.46
    MLLoader
    0.46
    Activations Density 0.200%

    No Known Activations