© 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
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2772
    Prev
    Next
    INDEX
    Explanations

    references to joint initiatives or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spannung
    -0.36
     stuk
    -0.36
    isesti
    -0.36
    ścioła
    -0.35
    $)$
    -0.35
     Gucci
    -0.34
    versorgung
    -0.34
    وردار
    -0.34
    sula
    -0.34
     caras
    -0.34
    POSITIVE LOGITS
     Joint
    1.18
     JOINT
    1.07
     joint
    1.05
     Joints
    1.02
    Joint
    1.01
    joint
    0.97
     joints
    0.96
    JOINT
    0.90
     Join
    0.86
    joints
    0.82
    Activations Density 0.250%

    No Known Activations