© 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. 13-GEMMASCOPE-RES-16K
    6. 8094
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to interdisciplinary and collaborative research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intérieur
    -0.42
     pinggang
    -0.40
     perdida
    -0.40
     derro
    -0.39
    tentu
    -0.38
    forhold
    -0.36
     négatif
    -0.36
    ujesz
    -0.35
     niega
    -0.35
    acidade
    -0.35
    POSITIVE LOGITS
    跨
    0.74
     cross
    0.72
     Mixed
    0.72
     mixed
    0.71
     inter
    0.65
    Mixed
    0.65
    makeConstraints
    0.65
    mixed
    0.65
     trans
    0.60
     multime
    0.60
    Activations Density 0.597%

    No Known Activations