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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 820
    Prev
    Next
    INDEX
    Explanations

    ingredients and measurements related to cooking or food preparation

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

    preparing ingredients and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.58
    HostException
    -0.52
    MessageOf
    -0.51
     שוליים
    -0.49
    Viitteet
    -0.47
     Wartung
    -0.47
    verwijspagina
    -0.46
    ⟬
    -0.46
    Билгалдахарш
    -0.46
    +#+
    -0.45
    POSITIVE LOGITS
    SequentialGroup
    0.54
    <?
    0.47
     initComponents
    0.47
    Procedimiento
    0.41
     prepared
    0.40
    iprot
    0.38
     bowls
    0.38
    Prepare
    0.37
     optional
    0.37
     preparation
    0.37
    Activations Density 0.005%

    No Known Activations