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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8194
    Prev
    Next
    INDEX
    Explanations

    syntax elements used in programming code

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

    continuing text, code, or legal citations

    np_acts-logits-general · gemini-2.0-flash

    continuation shown as (continued)

    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
    featureID
    -0.66
    basicConfig
    -0.65
    AndEndTag
    -0.59
     MaterialApp
    -0.59
    Portail
    -0.58
     betweenstory
    -0.58
    addCriterion
    -0.58
    WriteTagHelper
    -0.55
    Искәрмәләр
    -0.54
     dAtA
    -0.54
    POSITIVE LOGITS
     continued
    3.06
    continue
    2.99
     continue
    2.88
     continues
    2.71
    continued
    2.67
     continuing
    2.65
     Continued
    2.44
    Continued
    2.35
     Continue
    2.33
    continues
    2.30
    Activations Density 0.190%

    No Known Activations