© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 30973
    Prev
    Next
    INDEX
    Explanations

    segments of text that indicate the completion or approval of processes

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

    expressions of thanks and good wishes

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

    the end-of-turn/end-of-sequence marker (boundary between turns or segments).

    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
    cassert
    -0.32
     familiar
    -0.29
     zná
    -0.27
     láp
    -0.27
     obvious
    -0.26
     académica
    -0.26
     judiciaire
    -0.26
     domésticos
    -0.26
     bekannte
    -0.25
    RuleContext
    -0.25
    POSITIVE LOGITS
     typelib
    0.64
    expandindo
    0.64
    ፩
    0.62
    OGND
    0.60
     zwiſchen
    0.59
    rateful
    0.57
     queſta
    0.56
    +#+
    0.56
    Anonym
    0.55
    HomeAsUpEnabled
    0.55
    Activations Density 0.114%

    No Known Activations