© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4497
    Prev
    Next
    INDEX
    Explanations

    references to adult individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    medical references to adults and clinical contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     telefónica
    -0.37
     Whyte
    -0.35
     magnétique
    -0.35
     way
    -0.35
     Howe
    -0.34
     wave
    -0.34
     them
    -0.33
     esquí
    -0.33
     this
    -0.33
    getCause
    -0.33
    POSITIVE LOGITS
    Adult
    1.40
     adult
    1.38
    adult
    1.34
     Adult
    1.33
     ADULT
    1.24
     Adults
    1.20
     adults
    1.19
    Adults
    1.17
    adults
    1.09
     adulto
    1.09
    Activations Density 0.049%

    No Known Activations