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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15670
    Prev
    Next
    INDEX
    Explanations

    terms related to political and economic accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.80
     >=",
    -0.77
    COUVER
    -0.74
    DoubleQuotes
    -0.68
     nakalista
    -0.64
     sociala
    -0.58
     avoient
    -0.55
    RenderAtEndOf
    -0.54
     EconPapers
    -0.52
    googleapis
    -0.52
    POSITIVE LOGITS
     linger
    0.51
     lingers
    0.47
     disaster
    0.47
     zove
    0.45
     BoxDecoration
    0.45
     Terraria
    0.45
    UrlResolution
    0.45
    TagHelper
    0.45
    égal
    0.44
     monstruo
    0.43
    Activations Density 0.790%

    No Known Activations