© 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. 2-GEMMASCOPE-RES-16K
    11. 15138
    Prev
    Next
    INDEX
    Explanations

    terms related to signals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.54
    TintMode
    -0.50
     CanadaChoose
    -0.44
    IMPACT
    -0.41
    SceneManagement
    -0.40
    setAge
    -0.39
    Chairs
    -0.39
    thums
    -0.38
    placer
    -0.38
     infallib
    -0.38
    POSITIVE LOGITS
     signal
    1.10
     signals
    1.06
     Signals
    1.04
     Signal
    1.02
    Signal
    0.99
    Signals
    0.95
    signals
    0.94
    signal
    0.92
     SIGNAL
    0.92
    信号
    0.88
    Activations Density 0.068%

    No Known Activations