© 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. 13-GEMMASCOPE-RES-16K
    6. 8785
    Prev
    Next
    INDEX
    Explanations

    html tags and related code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sto
    -0.32
    uy
    -0.31
     child
    -0.31
     Church
    -0.28
     than
    -0.28
     nobody
    -0.27
     church
    -0.27
    cessite
    -0.26
     self
    -0.26
    IFICA
    -0.26
    POSITIVE LOGITS
     EconPapers
    0.98
    TagMode
    0.87
    tagHelperRunner
    0.84
    SourceChecksum
    0.78
     TestBed
    0.76
     surla
    0.76
     ProtoMessage
    0.75
     שוליים
    0.75
     समीक्षक
    0.71
    sizeCache
    0.70
    Activations Density 0.914%

    No Known Activations