© 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 EvalsExportsinterp-engineNEWAPI 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. 3203
    Prev
    Next
    INDEX
    Explanations

    names and familial relationships in an obituary context

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

    "bootstrapcdn" and related website code

    np_acts-logits-general · gemini-2.0-flash

    bootstrap links

    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
     invokingState
    -0.47
    Gambas
    -0.47
    Hentet
    -0.44
    endpush
    -0.43
     hooking
    -0.43
     resourceCulture
    -0.42
    ContentAlignment
    -0.40
    GeneratedMessage
    -0.40
    principalColumn
    -0.40
    bitField
    -0.40
    POSITIVE LOGITS
     feroit
    0.53
     garçons
    0.51
    ſelf
    0.51
     enfans
    0.49
    bootstrapcdn
    0.48
     Infór
    0.48
     pouvoit
    0.47
    ſcher
    0.46
     berdua
    0.46
     larmes
    0.45
    Activations Density 0.009%

    No Known Activations