© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14204
    Prev
    Next
    INDEX
    Explanations

    indicators of quality and support in various contexts

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

    Chemical concentrations (mM, ml)

    np_acts-logits-general · gemini-2.0-flash

    concentrations and medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ServletException
    -0.44
     Ganzen
    -0.43
    løs
    -0.39
    awaran
    -0.39
     enfans
    -0.37
     spôso
    -0.37
     proceeded
    -0.35
     coincided
    -0.35
     has
    -0.35
     that
    -0.35
    POSITIVE LOGITS
     pinulongan
    0.74
    extAlignment
    0.67
    thâu
    0.66
    
    0.66
    RTGC
    0.64
     հղումներ
    0.64
    featureID
    0.63
     Савезне
    0.63
     kaarangay
    0.63
     Normdatei
    0.61
    Activations Density 0.593%

    No Known Activations