© 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. 4137
    Prev
    Next
    INDEX
    Explanations

    references to collaboration, research authorship, and legislative actions

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

    that introduce an opinion or argument

    np_acts-logits-general · gemini-2.0-flash

    foreign or technical identifiers

    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
    出版年
    -0.39
     okuyayım
    -0.36
    getDoctrine
    -0.33
    ]^
    -0.31
     рассказыва
    -0.30
    bottomrule
    -0.29
    bullet
    -0.29
    })`
    -0.29
     shall
    -0.29
    bij
    -0.29
    POSITIVE LOGITS
    withIdentifier
    0.53
     flocked
    0.52
     gerne
    0.51
    กัน
    0.50
    纷纷
    0.49
     กัน
    0.47
     мәкал
    0.47
     enten
    0.44
    Manbalar
    0.44
    ⟭
    0.44
    Activations Density 0.577%

    No Known Activations