© 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. 34-GEMMASCOPE-RES-16K
    11. 12810
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons, particularly involving data or estimations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.53
    EFIAPI
    -0.47
    expandindo
    -0.46
    IntoConstraints
    -0.45
     jsPsych
    -0.45
    stateMutability
    -0.43
    WriteBarrier
    -0.43
    mography
    -0.42
    شهاد
    -0.40
    ="@+
    -0.40
    POSITIVE LOGITS
     actual
    3.38
    actual
    3.06
    Actual
    2.84
     ACTUAL
    2.83
     Actual
    2.73
    ACTUAL
    2.59
     actually
    2.55
     tatsäch
    2.42
    actually
    2.30
    真正的
    2.22
    Activations Density 2.623%

    No Known Activations