© 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. 6538
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and locations

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

    First part of names

    np_acts-logits-general · gemini-2.0-flash

    place names and proper nouns

    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
     الحره
    -0.80
    MLLoader
    -0.79
    CrossRef
    -0.78
    ImageContext
    -0.73
     autorytatywna
    -0.72
    featureID
    -0.69
     Normdatei
    -0.68
    tagHelperRunner
    -0.67
    RenderAtEndOf
    -0.66
     AssemblyProduct
    -0.65
    POSITIVE LOGITS
     hierogly
    0.61
    venidos
    0.58
     nachos
    0.55
     ricotta
    0.55
    ^(@)
    0.51
     raccoon
    0.51
     Indian
    0.51
     boughs
    0.51
     Etrus
    0.50
     Ruman
    0.50
    Activations Density 0.502%

    No Known Activations