© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3444
    Prev
    Next
    INDEX
    Explanations

    assertive and declarative statements regarding facts or mechanisms

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

    Sentences starting with "That is" or similar

    np_acts-logits-general · gemini-2.0-flash

    that is

    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
    featureID
    -0.58
    MethodManager
    -0.50
    Hentet
    -0.48
    szám
    -0.47
     الحره
    -0.45
    AutoScale
    -0.45
     Cuthbert
    -0.44
    Seasons
    -0.44
    EndGlobalSection
    -0.42
    recated
    -0.42
    POSITIVE LOGITS
     مواليد
    0.42
    Сылтамалар
    0.42
     why
    0.41
     whereof
    0.40
     who
    0.38
     that
    0.37
     EconPapers
    0.36
     препратки
    0.36
    thenReturn
    0.36
     same
    0.36
    Activations Density 0.092%

    No Known Activations