© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5401
    Prev
    Next
    INDEX
    Explanations

    properties and methods related to mathematical functions and exceptions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
    enumi
    -0.85
     Roskov
    -0.83
    ViewFeatures
    -0.81
    تقاوى
    -0.80
    Personendaten
    -0.76
    cshtml
    -0.74
     Biôgrafia
    -0.74
    providedIn
    -0.72
    contentLoaded
    -0.72
     незавершена
    -0.72
    POSITIVE LOGITS
     része
    0.46
     noastre
    0.44
     taas
    0.39
    ERICAL
    0.38
     spørs
    0.38
    </b>
    0.38
    をお願い
    0.37
     olympiques
    0.36
    cendental
    0.35
     oameni
    0.35
    Activations Density 0.211%

    No Known Activations