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. 17-GEMMASCOPE-RES-16K
    6. 5896
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships within a technical or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEX
    -0.57
    PhysRev
    -0.57
     EconPapers
    -0.57
     שוליים
    -0.56
    Pratique
    -0.54
    arXiv
    -0.54
     zufolge
    -0.52
     Support
    -0.52
    askar
    -0.51
    CrossRef
    -0.51
    POSITIVE LOGITS
    enumii
    0.60
    醐
    0.55
    enumi
    0.50
    abestanden
    0.49
     CWE
    0.47
     RouterModule
    0.47
    sery
    0.46
    fromnode
    0.45
     createSlice
    0.45
     placebo
    0.45
    Activations Density 0.454%

    No Known Activations