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. 6414
    Prev
    Next
    INDEX
    Explanations

    details surrounding events and circumstances related to distress or unusual situations

    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
    UnusedPrivate
    -0.53
     getItemId
    -0.52
    AddTagHelper
    -0.49
    pexpr
    -0.43
    Parcelize
    -0.42
     CreateTagHelper
    -0.41
    EndInit
    -0.41
    setCellValue
    -0.40
     još
    -0.40
    zbęd
    -0.39
    POSITIVE LOGITS
     strange
    0.59
    Strange
    0.58
     suspiciously
    0.56
     suspicious
    0.53
     odd
    0.53
     Strange
    0.52
     strangest
    0.50
     '\\;'
    0.50
     wierd
    0.50
     mysterious
    0.50
    Activations Density 0.317%

    No Known Activations