© 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. 21-GEMMASCOPE-RES-16K
    11. 1612
    Prev
    Next
    INDEX
    Explanations

    conjunctions and references to relationships among elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    they
    -0.66
    if
    -0.62
     they
    -0.61
     stuff
    -0.60
     thingy
    -0.59
    plus
    -0.59
    They
    -0.57
    no
    -0.57
    K
    -0.57
    L
    -0.56
    POSITIVE LOGITS
    )";
    0.85
    .}(
    0.85
    ">:
    0.84
    ^(@)
    0.81
    ^(@
    0.81
    ++
    0.81
    }")
    0.81
    $$
    0.80
    PERTIES
    0.80
    ".
    0.80
    Activations Density 0.459%

    No Known Activations