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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3594
    Prev
    Next
    INDEX
    Explanations

    programming language constructs, particularly types and templates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.91
    to
    -1.72
     To
    -1.32
    到
    -1.28
    To
    -1.25
     TO
    -1.23
    DataTo
    -1.17
    tothe
    -1.13
     чтобы
    -1.11
     إلى
    -1.10
    POSITIVE LOGITS
    :✨
    0.54
     kasarigan
    0.53
    NameInMap
    0.46
    erapeu
    0.45
     AssemblyCompany
    0.44
    ScopeManager
    0.44
    ांकि
    0.43
    leetcode
    0.43
     referenties
    0.43
    TRIBUTION
    0.41
    Activations Density 1.716%

    No Known Activations