© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 38527
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to algebra and sequences

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

    Douglas algebra

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    yelitis
    -0.57
     invokingState
    -0.54
     BoxFit
    -0.53
    ngdoc
    -0.52
    SourceChecksum
    -0.52
    دانشنامهٔ
    -0.52
     المعيارى
    -0.51
    ighborhood
    -0.51
    DMETHOD
    -0.51
    KURZBESCHREIBUNG
    -0.50
    POSITIVE LOGITS
    老
    0.36
     apă
    0.34
    ブル
    0.34
     老
    0.32
     Old
    0.32
     históricas
    0.31
     urbanas
    0.31
     florales
    0.30
     historique
    0.30
    httphttps
    0.30
    Activations Density 0.174%

    No Known Activations