© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13660
    Prev
    Next
    INDEX
    Explanations

    terms related to elastic materials, safety, and secure attachments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Adjustable bands or belts

    np_acts-logits-general · gemini-2.0-flash

    tight wrap around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.52
    存于互联网档案馆
    -0.50
    featureID
    -0.47
    RTLU
    -0.44
     <>",
    -0.43
     صوتيه
    -0.42
    __*/
    -0.41
     tipped
    -0.40
     تكبرها
    -0.39
    colhead
    -0.39
    POSITIVE LOGITS
     tighter
    0.58
     tightened
    0.57
     Wrap
    0.57
     tight
    0.57
     wrap
    0.56
    wrap
    0.55
    Wrap
    0.55
     wra
    0.54
     tightening
    0.54
    tight
    0.54
    Activations Density 0.236%

    No Known Activations