© 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. 9-GEMMASCOPE-RES-16K
    11. 1409
    Prev
    Next
    INDEX
    Explanations

    phrases that signal transitions or conclusions in a narrative

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

    "so" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    and so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mesmas
    -0.45
     auroit
    -0.44
     ocasião
    -0.42
    žad
    -0.41
     eivät
    -0.41
    foglal
    -0.40
    NewUrlParser
    -0.40
     liitty
    -0.39
     citoy
    -0.38
    ʖ
    -0.38
    POSITIVE LOGITS
    KommentareTeilen
    0.66
     sánh
    0.48
     Persson
    0.47
    MLLoader
    0.47
    ForResult
    0.47
    InteropServices
    0.46
     Sandwich
    0.46
     archiv
    0.46
    ldorf
    0.45
    etton
    0.44
    Activations Density 0.195%

    No Known Activations