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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13206
    Prev
    Next
    INDEX
    Explanations

    references to film critics and their opinions

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

    Film/music review publication and critic

    np_acts-logits-general · gemini-2.0-flash

    names after critic or by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     '\\;'
    -0.69
    Geplaatst
    -0.65
    Rüyada
    -0.59
    RepeatedField
    -0.59
     IndexPath
    -0.57
     poveznice
    -0.56
     storie
    -0.56
    tuigen
    -0.55
     stories
    -0.54
     SafeMath
    -0.53
    POSITIVE LOGITS
     critic
    1.13
     critical
    1.05
     crítico
    0.99
    critical
    0.97
     review
    0.96
     critics
    0.96
     reviews
    0.96
     reviewer
    0.96
     reviewing
    0.94
    Critical
    0.94
    Activations Density 0.250%

    No Known Activations