© 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. 9-GEMMASCOPE-RES-131K
    11. 126457
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that contain personal pronouns and references to individual identity

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

    start of sentence/turn

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that mark the speaker or system/meta annotations (e.g., the "model" token and start-of-turn/begin-of-sequence markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     avoient
    -0.48
     kasarigan
    -0.43
     fortæ
    -0.43
    numerusform
    -0.41
    SourceChecksum
    -0.41
     muligt
    -0.41
    AddTagHelper
    -0.41
    aktery
    -0.41
     även
    -0.40
     giudi
    -0.40
    POSITIVE LOGITS
     GenerationType
    0.51
     mergeFrom
    0.50
    ագրություններ
    0.46
     hObject
    0.46
     '\\;'
    0.46
     חיצוניים
    0.44
     utafitiHapana
    0.43
    ParallelGroup
    0.40
     везе
    0.39
    IntoConstraints
    0.39
    Activations Density 0.000%

    No Known Activations