© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1423
    Prev
    Next
    INDEX
    Explanations

    phrases and terms indicating the presence of evidence or claims, particularly in a critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.73
     "..\..\..\
    -0.69
     resourceCulture
    -0.67
    CodeAttribute
    -0.66
     "..\..\
    -0.65
    
    -0.64
    EDEFAULT
    -0.63
     estekak
    -0.63
    simpleType
    -0.63
     nahilalakip
    -0.60
    POSITIVE LOGITS
     evidence
    2.43
     proof
    2.36
    evidence
    2.12
     Evidence
    2.05
    Evidence
    2.03
     EVIDENCE
    2.00
     PROOF
    1.96
     Proof
    1.95
    proof
    1.91
    Proof
    1.90
    Activations Density 1.307%

    No Known Activations