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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10994
    Prev
    Next
    INDEX
    Explanations

    elements related to family planning and reproductive intentions

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

    Tokens after certain verbs

    np_acts-logits-general · gemini-2.0-flash

    probability or possibility

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    HtmlAttribute
    -0.53
    internalType
    -0.51
     للاسماء
    -0.49
    bootstrapcdn
    -0.48
     chrétien
    -0.48
     myſelf
    -0.47
     Theſe
    -0.47
     Diſ
    -0.47
     serpiente
    -0.46
    MLLoader
    -0.45
    POSITIVE LOGITS
    adaptiveStyles
    0.43
     IFTT
    0.41
     vaz
    0.38
    thâu
    0.36
    #
    0.36
     canlynol
    0.34
    xodo
    0.34
    Jîn
    0.34
    /*
    0.33
     because
    0.33
    Activations Density 0.495%

    No Known Activations