© 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. 36-GEMMASCOPE-RES-16K
    11. 7446
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing or discussing evidence in a scientific or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFieldSet
    -0.43
    InitVars
    -0.42
     nakalista
    -0.41
    tagHelperRunner
    -0.40
    windowFixed
    -0.40
    
    -0.38
    Begriffsklä
    -0.38
    FormTagHelper
    -0.38
     '\\;'
    -0.37
    ագրություններ
    -0.36
    POSITIVE LOGITS
     evidence
    2.84
    evidence
    2.45
     Evidence
    2.28
    Evidence
    2.27
     EVIDENCE
    2.22
     proof
    2.17
     evidences
    1.91
    证据
    1.91
     evidencia
    1.88
     bukti
    1.73
    Activations Density 1.558%

    No Known Activations