© 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. 13790
    Prev
    Next
    INDEX
    Explanations

    specific names and terminology related to sports and legal concepts

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

    Tokens appearing before numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    legal and technical terms

    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
     فريبيس
    -0.73
     المعيارى
    -0.69
     AssemblyCulture
    -0.67
    ſelf
    -0.58
     SwitchCompat
    -0.58
    OGND
    -0.57
    GOTREF
    -0.56
     Demo
    -0.56
     виправивши
    -0.55
     houſe
    -0.55
    POSITIVE LOGITS
    ftagPool
    0.46
     Bestimmungen
    0.40
     geçir
    0.40
     Draht
    0.35
     Größen
    0.34
     edil
    0.34
     pattes
    0.34
    SizeF
    0.33
     Empfindung
    0.33
     reichen
    0.33
    Activations Density 1.227%

    No Known Activations