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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14740
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "short" in various contexts

    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
     EventEmitter
    -0.50
    Vey
    -0.50
    ceus
    -0.48
    DotNetBar
    -0.48
    Бахар
    -0.47
    ostante
    -0.46
     mView
    -0.46
    TEntity
    -0.46
    atrix
    -0.45
    riwal
    -0.44
    POSITIVE LOGITS
     short
    1.29
    Short
    1.25
     SHORT
    1.23
     Short
    1.22
    short
    1.17
    SHORT
    1.15
     corto
    1.05
     fhort
    1.05
    短
    0.94
     cortos
    0.94
    Activations Density 0.114%

    No Known Activations