© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15920
    Prev
    Next
    INDEX
    Explanations

    references to political speech and judicial conduct 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
    раздо
    -0.43
     Bretaña
    -0.41
     royaume
    -0.41
     retrouvé
    -0.40
     dalamnya
    -0.37
    apatalk
    -0.36
     británico
    -0.36
     Daß
    -0.35
    erialized
    -0.35
     विश्वसनीयता
    -0.34
    POSITIVE LOGITS
     الحره
    0.47
     candidate
    0.45
    arnes
    0.45
     kaarangay
    0.45
     voters
    0.45
     Candidate
    0.44
     pledges
    0.44
    ReusableCell
    0.44
    candidate
    0.43
    Flan
    0.43
    Activations Density 0.433%

    No Known Activations