© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6515
    Prev
    Next
    INDEX
    Explanations

    topics related to neuronal biology and diseases

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

    "Understanding" followed by scientific topics

    np_acts-logits-general · gemini-2.0-flash

    seeking to understand

    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
     habría
    -0.46
     
    -0.46
     quedarse
    -0.45
     rask
    -0.44
    ographiques
    -0.44
     auraient
    -0.42
     refuser
    -0.42
     פי
    -0.42
     habrían
    -0.42
    AddWithValue
    -0.41
    POSITIVE LOGITS
     dynamics
    0.94
     interactions
    0.94
     processes
    0.86
     interaction
    0.82
     mechanisms
    0.82
     interplay
    0.81
     relationships
    0.81
     behaviour
    0.80
     understanding
    0.79
     Interactions
    0.78
    Activations Density 1.030%

    No Known Activations