© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15895
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "meme" and its variations, indicating a focus on concepts of sameness or identity

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.52
     aldri
    -0.47
     rarement
    -0.45
     bislang
    -0.44
    bbene
    -0.44
     contributo
    -0.43
    =""><
    -0.42
     ciento
    -0.42
     llevo
    -0.41
    ofern
    -0.41
    POSITIVE LOGITS
    same
    2.73
     same
    2.71
    Same
    2.66
     Same
    2.49
    SAME
    2.40
     SAME
    2.20
     mismo
    2.00
     misma
    1.92
     mesma
    1.86
     mismos
    1.83
    Activations Density 0.216%

    No Known Activations