© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14962
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions and efforts aimed at achieving specific outcomes

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

    "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PageModule
    -0.51
    makeConstraints
    -0.47
    argout
    -0.43
    ContentAsync
    -0.41
    Vtbl
    -0.40
    ">{{$
    -0.39
    detectChanges
    -0.39
     brev
    -0.37
    Dif
    -0.36
     IDisposable
    -0.35
    POSITIVE LOGITS
     اینکه
    0.61
     ervoor
    0.55
     '\\;'
    0.53
     ensuring
    0.52
    orsese
    0.50
     чтобы
    0.49
     ensure
    0.49
     sicherzustellen
    0.48
     faktiskt
    0.47
     betrekking
    0.47
    Activations Density 0.334%

    No Known Activations