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 - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 951
    Prev
    Next
    INDEX
    Explanations

    information related to genetic or cellular processes and their effects or significance

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

    Preposition "of"

    np_acts-logits-general · gemini-2.0-flash

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     snippetHide
    -0.42
    setContentView
    -0.38
     kyllä
    -0.37
     Sied
    -0.37
     provecho
    -0.36
    bewerken
    -0.35
     Stuhl
    -0.35
     mostrarán
    -0.35
    клопе
    -0.35
    liesslich
    -0.35
    POSITIVE LOGITS
    Autoritní
    0.51
     having
    0.47
    endregion
    0.47
    VIATIONS
    0.46
    Having
    0.44
     anonymity
    0.42
     <=",
    0.42
     Having
    0.41
    ulgação
    0.40
    <()>
    0.40
    Activations Density 0.467%

    No Known Activations