© 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-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1538
    Prev
    Next
    INDEX
    Explanations

    references to various "format" types and their related attributes in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    expandindo
    -0.42
    peer
    -0.42
     peer
    -0.42
    Personne
    -0.41
     vicenda
    -0.41
    Peer
    -0.40
     mouse
    -0.39
    XmlNode
    -0.39
     OkHttpClient
    -0.39
    Pe
    -0.39
    POSITIVE LOGITS
     Format
    1.53
     format
    1.48
    Format
    1.47
    format
    1.46
     FORMAT
    1.39
     Formats
    1.38
     formats
    1.30
    FORMAT
    1.16
    Formats
    1.13
    formats
    1.09
    Activations Density 0.097%

    No Known Activations