© 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 EvalsExportsinterp-engineNEWAPI 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. 11008
    Prev
    Next
    INDEX
    Explanations

    incidents related to injury or trauma

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

    Informal, conversational language

    np_acts-logits-general · gemini-2.0-flash

    informal speech and exclamations

    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
     siguran
    -0.56
     voordeel
    -0.46
     wygod
    -0.43
     obecnie
    -0.43
     durchaus
    -0.43
     verhind
    -0.42
     traccia
    -0.41
     alcuna
    -0.41
     voldoende
    -0.41
     vrijwilli
    -0.39
    POSITIVE LOGITS
     fuckin
    0.60
     freaking
    0.59
     freakin
    0.57
    featureID
    0.56
    HasAnnotation
    0.55
     fucking
    0.54
    basically
    0.52
     dude
    0.50
     guy
    0.50
    literally
    0.50
    Activations Density 0.229%

    No Known Activations