© 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. 6344
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or outcomes

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

    "Lead to" or "leads to"

    np_acts-logits-general · gemini-2.0-flash

    leads to outcome

    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
    ToUpdate
    -0.42
     exercício
    -0.41
    ndag
    -0.41
    ItemIndex
    -0.40
    دانشنامهٔ
    -0.39
    原始内容存档于
    -0.39
     estekak
    -0.39
    InfoService
    -0.38
     Gesch
    -0.38
     strictly
    -0.38
    POSITIVE LOGITS
     resulting
    0.76
     resulted
    0.73
    resulting
    0.72
     entraîne
    0.66
     leads
    0.66
    导致
    0.65
    DockStyle
    0.63
    Leads
    0.62
     melahirkan
    0.62
    leads
    0.62
    Activations Density 0.345%

    No Known Activations