© 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 EvalsExportsAPI 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. 4392
    Prev
    Next
    INDEX
    Explanations

    names and relationships within family structures

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

    before or after names, numbers, hyphenated terms

    np_acts-logits-general · gemini-2.0-flash

    Nick.9 yearsfair-minded-G-usual differentiation

    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
    IsContent
    -0.63
     otomatig
    -0.56
     дописавши
    -0.53
    RTEE
    -0.53
     henvisninger
    -0.49
    XmlAccessType
    -0.49
     OFDb
    -0.48
    Tikang
    -0.47
     للمعارف
    -0.47
    principalColumn
    -0.46
    POSITIVE LOGITS
    __*/
    0.38
     Numerade
    0.36
    Their
    0.35
     their
    0.35
     intStringLen
    0.34
    ajoz
    0.34
     CGSize
    0.33
    <?
    0.33
    他們的
    0.33
     Their
    0.33
    Activations Density 0.024%

    No Known Activations