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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 31-GEMMASCOPE-RES-16K
    6. 3017
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and related formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    structural formatting elements like line breaks, quoted sections, and paragraph separators.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.56
    הערות
    -0.52
    CppMethod
    -0.52
    ISupport
    -0.50
     CreateTagHelper
    -0.47
    multer
    -0.47
    protoc
    -0.47
    WriteTagHelper
    -0.47
     <=",
    -0.47
    توض
    -0.46
    POSITIVE LOGITS
    IndentedString
    0.48
    ließlich
    0.47
    Tarih
    0.45
    Harmon
    0.45
    sprogramm
    0.43
    écnicas
    0.40
    Література
    0.40
     oignons
    0.38
     ,"
    0.38
    Systematic
    0.37
    Activations Density 0.259%

    No Known Activations