© 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. 3299
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of the verb "have" and its variations

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

    Following forms of "to be" verbs

    np_acts-logits-general · gemini-2.0-flash

    past participles and states

    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
    <strong>
    -0.44
    ↵↵
    -0.35
     first
    -0.35
    (
    -0.35
    </h2>
    -0.33
    }
    -0.32
    first
    -0.32
    H
    -0.32
     
    -0.31
     H
    -0.30
    POSITIVE LOGITS
     للمعارف
    0.89
    rungsseite
    0.80
     betweenstory
    0.80
     surla
    0.80
     PeEnEo
    0.79
     AssemblyCulture
    0.78
     estekak
    0.76
     tartalomajánló
    0.76
     queſta
    0.74
     ویکی‌پدی
    0.72
    Activations Density 0.403%

    No Known Activations