Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23588
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Personendaten
    -0.30
     виправивши
    -0.28
     apud
    -0.27
    Autoritní
    -0.27
     piemē
    -0.27
    freopen
    -0.26
     Roskov
    -0.26
     tých
    -0.25
    RTEE
    -0.25
     estabilidad
    -0.25
    POSITIVE LOGITS
     dieſer
    0.85
     zwiſchen
    0.79
     dieſen
    0.78
     ſeinen
    0.77
     wiſſen
    0.77
     unſer
    0.76
     deſſen
    0.76
     dieſes
    0.75
     ſeinem
    0.74
     Geiſt
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.