© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4524
    Prev
    Next
    INDEX
    Explanations

    terms related to identification and acknowledgment

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     
    -0.55
    </em>
    -0.52
    O
    -0.52
     luxe
    -0.51
     bot
    -0.51
    ecake
    -0.50
    (/^
    -0.50
     Sarah
    -0.50
     htons
    -0.49
    々
    -0.49
    POSITIVE LOGITS
     identification
    2.44
     Identified
    2.37
     identify
    2.32
     identified
    2.31
     identifying
    2.31
     Identify
    2.31
     identifies
    2.31
     identific
    2.28
     Identi
    2.20
    identification
    2.19
    Activations Density 0.073%

    No Known Activations