© 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. 11926
    Prev
    Next
    INDEX
    Explanations

    instances of future tense verbs indicating intention, prediction, or possibility

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

    "will" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    will followed by a verb

    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
     ir
    -0.37
    گاب
    -0.36
     sem
    -0.35
     chiefly
    -0.35
    CppCodeGen
    -0.34
    featureID
    -0.34
    utusan
    -0.33
    centralwidget
    -0.33
     chapter
    -0.32
     ins
    -0.32
    POSITIVE LOGITS
    +#+
    0.59
    pecabe
    0.58
    AsUp
    0.57
     AssemblyCulture
    0.54
    majánló
    0.52
     '\\;'
    0.52
     transfieras
    0.51
    koľvek
    0.50
    Dobrý
    0.50
    KommentareTeilen
    0.50
    Activations Density 0.152%

    No Known Activations