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. 18-GEMMASCOPE-RES-16K
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    examples or cases related to specific phenomena or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows words like "example," "typical," or "embodiment."

    np_acts-logits-general · gemini-2.0-flash

    being a typical example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.79
     informée
    -0.58
    Carriera
    -0.58
    tagHelperRunner
    -0.55
    rizona
    -0.54
    FilterChain
    -0.52
     Réponses
    -0.51
     >=",
    -0.51
    WriteTagHelper
    -0.51
     ISNI
    -0.51
    POSITIVE LOGITS
     exemplify
    1.69
     example
    1.64
     exemplifies
    1.58
     examples
    1.55
     representative
    1.48
     Examples
    1.42
     exemplar
    1.39
     Beispiele
    1.37
     voorbeeld
    1.37
    example
    1.36
    Activations Density 0.350%

    No Known Activations