Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92690
    Prev
    Next
    INDEX
    Explanations

    future-oriented phrases that indicate certainty or potential outcomes

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

    providing future benefits or outcomes

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyCompany
    -0.48
    CloseOperation
    -0.44
     GenerationType
    -0.44
    ########.
    -0.43
     Möglich
    -0.38
     Distrito
    -0.36
    LOYE
    -0.36
    ulipas
    -0.35
    Erreferentziak
    -0.35
     ")");
    -0.35
    POSITIVE LOGITS
     your
    0.68
    المناصب
    0.53
    você
    0.52
     Paglinawan
    0.52
    your
    0.51
     YOUR
    0.51
     you
    0.51
    きっと
    0.50
     youll
    0.49
    inspire
    0.48
    Activations Density 0.008%

    No Known Activations