© 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
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2079
    Prev
    Next
    INDEX
    Explanations

    user interface elements and buttons related to product management or navigation

    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
     nakalista
    -0.74
     estekak
    -0.62
     NSCoder
    -0.59
    ConstraintMaker
    -0.59
     ModelExpression
    -0.54
    󠀠
    -0.54
    ressee
    -0.51
    VersionUID
    -0.49
    wiliwch
    -0.49
    ifikationer
    -0.49
    POSITIVE LOGITS
    DrawerToggle
    0.43
    VolleyError
    0.42
    EnableWeb
    0.41
     doInBackground
    0.40
    titleMargin
    0.35
    setdefault
    0.34
     Sin
    0.33
    tonode
    0.33
     sin
    0.32
     TestCase
    0.32
    Activations Density 0.204%

    No Known Activations