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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3908
    Prev
    Next
    INDEX
    Explanations

    components related to data extraction and handling error states in a programming context

    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
    ScopeManager
    -1.00
     betweenstory
    -0.93
    findpost
    -0.87
    fjspx
    -0.83
     unknownFields
    -0.76
     Réponses
    -0.75
    ReusableCell
    -0.74
    ">—
    -0.71
    IsMutable
    -0.71
    WebVitals
    -0.70
    POSITIVE LOGITS
    ชาติ
    0.50
     ten
    0.47
    دم
    0.46
     跳转至
    0.44
    Scénario
    0.43
    accro
    0.42
    Биография
    0.42
    CASCADE
    0.41
    Chloroform
    0.41
    ANTY
    0.40
    Activations Density 0.163%

    No Known Activations