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. 16-GEMMASCOPE-RES-16K
    6. 151
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific characters or names within the text

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

    First-person narrative viewpoint

    np_acts-logits-general · gemini-2.0-flash

    subject performing an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auroit
    -0.88
     étoit
    -0.85
     itſelf
    -0.83
     feroit
    -0.79
     kasarigan
    -0.79
     pouvoit
    -0.79
     iſt
    -0.76
     étoient
    -0.75
     lenker
    -0.74
    MigrationBuilder
    -0.72
    POSITIVE LOGITS
     then
    0.97
     knew
    0.72
     put
    0.64
     got
    0.62
     soon
    0.62
     was
    0.60
     went
    0.59
     had
    0.59
     sat
    0.58
     proceeded
    0.58
    Activations Density 0.345%

    No Known Activations