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. 19-GEMMASCOPE-RES-16K
    6. 475
    Prev
    Next
    INDEX
    Explanations

    references to specific examples or instances in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _));
    -0.68
    oa̍t
    -0.65
    inheritdoc
    -0.57
    urlpatterns
    -0.55
    Cyfeiriadau
    -0.54
    riek
    -0.54
    StoryboardSegue
    -0.54
    TargetException
    -0.54
     Meksiku
    -0.53
     FetchType
    -0.52
    POSITIVE LOGITS
     example
    2.65
     например
    2.58
     Например
    2.55
    Например
    2.49
     bijvoorbeeld
    2.40
     misalnya
    2.39
     beispielsweise
    2.30
    Example
    2.28
    例如
    2.25
     Misalnya
    2.22
    Activations Density 1.225%

    No Known Activations