Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7966
    Prev
    Next
    INDEX
    Explanations

    references to legal decisions and their implications on societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     saurait
    -0.48
    Hentet
    -0.44
    Personensuche
    -0.42
    Datuak
    -0.42
    ammans
    -0.41
     christlichen
    -0.41
    evaluation
    -0.39
     gratuita
    -0.37
    stags
    -0.37
    candidate
    -0.36
    POSITIVE LOGITS
     still
    0.79
     Still
    0.65
     ftill
    0.63
    Still
    0.60
    still
    0.59
     nadal
    0.57
     ainda
    0.56
     masih
    0.55
    依然
    0.54
     STILL
    0.54
    Activations Density 0.760%

    No Known Activations