© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 52287
    Prev
    Next
    INDEX
    Explanations

    conversational cues and responses in dialogues

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

    code blocks or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    Tokens that mark the start of an answer/assistant response (the "A" / "A:" answer-turn label).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.57
     rospy
    -0.50
    ImageContext
    -0.49
    Autoritní
    -0.46
    AndEndTag
    -0.45
    Gweler
    -0.44
     autorytatywna
    -0.43
    Slf
    -0.43
     ujednoznacz
    -0.42
     Grüsse
    -0.42
    POSITIVE LOGITS
    Personendaten
    0.45
    RenderAtEndOf
    0.45
    tonode
    0.43
    awtextra
    0.40
    Jeografia
    0.39
    HasForeignKey
    0.39
     noDo
    0.38
    ReactDOM
    0.36
    decoded
    0.35
    InstrumentedTest
    0.35
    Activations Density 0.565%

    No Known Activations