© 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. 25-GEMMASCOPE-RES-16K
    6. 9817
    Prev
    Next
    INDEX
    Explanations

    specific names and instances associated with characters, entities, or locations within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hébergement
    -0.53
    enfance
    -0.53
    assemblée
    -0.53
    entraînement
    -0.52
    extérieur
    -0.51
    équipement
    -0.51
    exécution
    -0.50
    émission
    -0.50
    hôpital
    -0.50
    étape
    -0.49
    POSITIVE LOGITS
    ea
    0.35
    ase
    0.35
    ant
    0.35
    ay
    0.34
    ale
    0.34
    ac
    0.34
    av
    0.34
    ead
    0.34
    ore
    0.34
    aires
    0.34
    Activations Density 17.281%

    No Known Activations