© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8428
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and manipulations involving variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -0.46
    <bos>
    -0.40
     tranquilidad
    -0.40
    一身
    -0.39
     अभ
    -0.39
    getDoctrine
    -0.38
    *
    -0.38
    .
    -0.37
     kacang
    -0.36
    oriam
    -0.36
    POSITIVE LOGITS
    posedge
    1.09
     мәкал
    1.07
    InjectAttribute
    1.02
    complexContent
    0.97
    تقاوى
    0.95
     betweenstory
    0.90
    ConstraintMaker
    0.88
    脚注の使い方
    0.86
    writeFieldEnd
    0.84
    RegistryLite
    0.84
    Activations Density 0.512%

    No Known Activations