© 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. 2-GEMMASCOPE-RES-16K
    11. 3254
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to proof and evidence

    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
     hot
    -0.71
    Hot
    -0.60
     Hot
    -0.60
    hot
    -0.55
    tshell
    -0.50
     HOT
    -0.50
    雳
    -0.49
     frente
    -0.48
    يميديا
    -0.48
    hicles
    -0.45
    POSITIVE LOGITS
     prove
    1.92
     proves
    1.70
     proving
    1.67
    prove
    1.62
     Prove
    1.60
     proof
    1.58
     proofs
    1.50
    Prove
    1.50
     proved
    1.41
     Proof
    1.40
    Activations Density 0.109%

    No Known Activations