© 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. 9-GEMMASCOPE-RES-16K
    11. 4468
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional distress or significant life events

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

    Japanese verbs ending in "る" or "いる"

    np_acts-logits-general · gemini-2.0-flash

    states of being or existence

    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
     kaarangay
    -0.90
     Roskov
    -0.69
    LookAnd
    -0.66
    нгред
    -0.66
    ましたが
    -0.65
    AnimationsModule
    -0.65
    いましたが
    -0.61
     gynhyrchwyd
    -0.61
     كومونز
    -0.60
    uxxxx
    -0.60
    POSITIVE LOGITS
    がある
    0.40
    が多い
    0.40
    つく
    0.39
    เยอะ
    0.38
    ことがある
    0.35
    ことが多い
    0.35
    Dziękuję
    0.35
    บ้าง
    0.34
     cardíaca
    0.34
    れている
    0.33
    Activations Density 0.125%

    No Known Activations