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

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9473
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with physical damage or tearing

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

    Actions involving tearing or damage

    np_acts-logits-general · gemini-2.0-flash

    tearing and ripping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andExpect
    -0.76
    IntoConstraints
    -0.72
     DBNull
    -0.71
    WebVitals
    -0.67
    featureID
    -0.65
    ChildIndex
    -0.65
    Бележки
    -0.64
    StructEnd
    -0.64
     Diſ
    -0.63
    NameInMap
    -0.63
    POSITIVE LOGITS
     tearing
    0.50
     déchir
    0.50
     tore
    0.47
     torn
    0.45
     ripping
    0.42
     ripped
    0.40
     tear
    0.39
     flesh
    0.35
    撕
    0.35
     Torn
    0.34
    Activations Density 0.145%

    No Known Activations