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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11460
    Prev
    Next
    INDEX
    Explanations

    sections and structure in academic or research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.42
    AddHtmlAttribute
    -0.37
    oredCriteria
    -0.36
    ynı
    -0.36
    baomidou
    -0.35
    WriteTagHelper
    -0.34
    Ӕ
    -0.34
    bcrypt
    -0.34
    SharedCtor
    -0.34
     base
    -0.33
    POSITIVE LOGITS
    FieldDescriptor
    0.49
    لينكات
    0.49
     considerations
    0.49
     AssemblyProduct
    0.49
     pourquoi
    0.48
    TypedDataSet
    0.47
    为什么
    0.46
    󠁢
    0.46
     nakalista
    0.45
    matchCondition
    0.45
    Activations Density 0.269%

    No Known Activations