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

    Neuronpedia

    APICircuit 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12762
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "to"

    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-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
    getStart
    -0.35
     ressemb
    -0.28
     avantage
    -0.28
     Independencia
    -0.28
     pří
    -0.27
     huvud
    -0.26
     dø
    -0.26
     صفحۀ
    -0.26
     нес
    -0.25
     Liebes
    -0.25
    POSITIVE LOGITS
    ChildScrollView
    0.89
     ddelwed
    0.83
    SBATCH
    0.83
    rotum
    0.82
    <unused8>
    0.81
    [@BOS@]
    0.81
    <unused41>
    0.81
    <unused74>
    0.81
    <unused47>
    0.81
    <pad>
    0.80
    Activations Density 0.516%

    No Known Activations