© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10738
    Prev
    Next
    INDEX
    Explanations

    terms related to actions or processes in various contexts

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

    changes or transfers

    np_acts-logits-general · gemini-2.0-flash

    actions, events, and transfers

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ContentValues
    -0.39
     lave
    -0.38
     BufferedWriter
    -0.37
    aság
    -0.36
    الإنجليزية
    -0.36
    currentColor
    -0.35
    AutoModerator
    -0.35
     Pandora
    -0.35
     IEnumerator
    -0.35
    userdata
    -0.35
    POSITIVE LOGITS
    ircut
    0.59
    ctomy
    0.59
     Fahrt
    0.58
    donation
    0.58
     caminhada
    0.57
     transferência
    0.56
     arrests
    0.56
    ครั้ง
    0.56
    onation
    0.56
     reversal
    0.55
    Activations Density 2.126%

    No Known Activations