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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5718
    Prev
    Next
    INDEX
    Explanations

    specific programming and code structure elements across various programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.91
     <<<<<<<<<<<<<<
    -0.88
    хьтан
    -0.87
    providedIn
    -0.84
    NUMX
    -0.84
     propOrder
    -0.83
    oa̍t
    -0.83
    Jereo
    -0.82
    StoryboardSegue
    -0.81
     فريبيس
    -0.81
    POSITIVE LOGITS
    RESH
    0.45
    достатки
    0.42
     
    0.42
     rast
    0.39
     needless
    0.38
    korn
    0.38
     musi
    0.36
    kast
    0.36
    isateur
    0.36
    standing
    0.36
    Activations Density 0.169%

    No Known Activations