© 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. 2730
    Prev
    Next
    INDEX
    Explanations

    elements related to wiring and electrical connections, as well as legal terminology related to defense and modification of claims

    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
     MediatR
    -0.38
    Asign
    -0.38
    boot
    -0.37
    skog
    -0.37
    ündigt
    -0.36
    ()?;
    -0.36
    SOUNDBITE
    -0.35
    Orsay
    -0.35
    zando
    -0.35
    weiter
    -0.35
    POSITIVE LOGITS
     porque
    0.61
     because
    0.60
    是因为
    0.59
     becauſe
    0.58
     '\\;'
    0.56
    Porque
    0.55
    because
    0.54
     omdat
    0.53
    :✨
    0.52
     perché
    0.52
    Activations Density 1.181%

    No Known Activations