© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7915
    Prev
    Next
    INDEX
    Explanations

    information related to geometric transformations and kinematic equations

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

    mathematical and spatial transformation concepts like rotation, translation, coordinates, matrices, and angles.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ɵɵ
    -0.68
     dib
    -0.49
     surla
    -0.48
    PYX
    -0.48
    tice
    -0.45
     Fascism
    -0.45
     CIC
    -0.45
     NBS
    -0.44
    niſſe
    -0.44
    ."],
    -0.44
    POSITIVE LOGITS
     Arque
    0.47
     Haltung
    0.45
     bēr
    0.45
    acamata
    0.43
     jaula
    0.43
     rigide
    0.42
     posisi
    0.42
     kamera
    0.42
     coordenadas
    0.42
     wię
    0.41
    Activations Density 0.165%

    No Known Activations