© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14796
    Prev
    Next
    INDEX
    Explanations

    frequent words indicative of relationships and connections between subjects in a text

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

    Following "the", "in", "of", "our", or "your"

    np_acts-logits-general · gemini-2.0-flash

    delivering the opportunity

    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
    GraphicsUnit
    -0.43
    IndentedString
    -0.41
     dovre
    -0.40
     menghindari
    -0.38
    gelöst
    -0.38
    StringBuilder
    -0.37
    ьаж
    -0.37
    The
    -0.37
     voelen
    -0.36
     I
    -0.36
    POSITIVE LOGITS
     ſta
    0.73
     kaarangay
    0.65
    UnknownFieldSet
    0.62
     poffe
    0.61
     ſch
    0.61
     myſelf
    0.59
     eſſ
    0.58
     ſte
    0.57
     purpoſe
    0.57
     itſelf
    0.57
    Activations Density 0.322%

    No Known Activations