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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11965
    Prev
    Next
    INDEX
    Explanations

    specific references to this and these in 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
     these
    -0.80
     solchen
    -0.71
     takiej
    -0.71
     this
    -0.70
    these
    -0.69
    それが
    -0.68
     taką
    -0.66
    そのような
    -0.63
    これが
    -0.63
     solches
    -0.63
    POSITIVE LOGITS
    SharedCtor
    0.67
    rungsseite
    0.63
    Geplaatst
    0.62
    tagHelperRunner
    0.59
    StoryboardSegue
    0.57
    Personensuche
    0.56
     resourceCulture
    0.54
    utilisons
    0.52
    BeginInit
    0.52
     sī
    0.52
    Activations Density 0.274%

    No Known Activations