Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7126
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility and ability

    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
    ?
    -0.32
    "]();
    -0.32
    ništ
    -0.29
     στις
    -0.28
    ponses
    -0.27
     unters
    -0.26
     समीक्षाओं
    -0.26
    UserScript
    -0.26
    ölle
    -0.25
     verboten
    -0.25
    POSITIVE LOGITS
    ניתן
    0.80
     ניתן
    0.80
    Podemos
    0.78
    CanBe
    0.75
    easily
    0.71
    Puedes
    0.71
     ويمكن
    0.71
     can
    0.71
     podemos
    0.70
     pouvons
    0.70
    Activations Density 0.555%

    No Known Activations