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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 23491
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to hierarchies or layers

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

    $\operatorname{G}_{F_m,X}$, $\operatorname{F}_{F_m,X}$

    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-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
     étudi
    -0.59
     esencial
    -0.58
     Recuperado
    -0.57
     przykład
    -0.57
    izoen
    -0.56
     miniaturka
    -0.55
     Sicherung
    -0.54
     Được
    -0.54
     chrétiens
    -0.54
     Corea
    -0.53
    POSITIVE LOGITS
    }_{
    0.74
     Gual
    0.49
    }_{(
    0.48
     bour
    0.47
     }_{
    0.47
    }^{
    0.47
    }}_{
    0.47
     BOUR
    0.46
     Kou
    0.46
    tolu
    0.46
    Activations Density 0.038%

    No Known Activations