© 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. 15-GEMMASCOPE-RES-16K
    6. 2160
    Prev
    Next
    INDEX
    Explanations

    terms related to projectiles and their physical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Again
    -0.40
     Again
    -0.39
     Lastly
    -0.34
    Lastly
    -0.34
     vuelva
    -0.33
     jäl
    -0.33
     again
    -0.33
    Wrapped
    -0.32
    Geplaatst
    -0.32
    商
    -0.32
    POSITIVE LOGITS
    endphp
    0.63
    encodeWith
    0.61
     IFTT
    0.60
    apimachinery
    0.58
     ब्रेकडाउन
    0.57
    UnsafeEnabled
    0.57
    MLLoader
    0.55
    addContainerGap
    0.55
    DockStyle
    0.54
     باخ
    0.54
    Activations Density 1.594%

    No Known Activations