© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 244
    Prev
    Next
    INDEX
    Explanations

    contextual references to coding errors and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    に
    -1.65
    에
    -0.77
    にの
    -0.63
    に来
    -0.53
    にします
    -0.52
    に限
    -0.52
    に似
    -0.51
    に進
    -0.49
    に使用
    -0.49
    に座
    -0.45
    POSITIVE LOGITS
     Wicidata
    0.40
    CrossRef
    0.39
     stump
    0.39
     OrderedDict
    0.38
     Perspective
    0.38
    )_/¯
    0.38
    JvmStatic
    0.38
     Lipa
    0.38
    migrationBuilder
    0.38
    :✨
    0.38
    Activations Density 0.181%

    No Known Activations