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. 5-GEMMASCOPE-RES-16K
    6. 8575
    Prev
    Next
    INDEX
    Explanations

    instances and operations related to stack manipulation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otheek
    -0.57
     sqlalchemy
    -0.57
    UnitTesting
    -0.55
     BoxDecoration
    -0.54
    PhysRevD
    -0.54
     مرئيه
    -0.53
    CodeAttribute
    -0.53
     gong
    -0.52
    люсы
    -0.50
     satel
    -0.50
    POSITIVE LOGITS
    dequeue
    0.83
    nextLine
    0.82
    ++]
    0.80
    pop
    0.76
    ]--;
    0.75
    pleft
    0.74
     -=
    0.73
    ReadLine
    0.72
     Exacts
    0.70
    --]
    0.69
    Activations Density 0.062%

    No Known Activations