© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15599
    Prev
    Next
    INDEX
    Explanations

    instances of structure and relationships within data or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.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
     Audiodateien
    -0.40
    Personendaten
    -0.40
    ientôt
    -0.37
     stället
    -0.36
    Datuak
    -0.36
    WritableDatabase
    -0.36
     Ambiental
    -0.35
     särskilt
    -0.35
     cherchés
    -0.34
     Stücke
    -0.34
    POSITIVE LOGITS
    copg
    0.54
    fection
    0.52
     surla
    0.52
    NNY
    0.51
     transfieras
    0.51
    tiness
    0.50
    kloped
    0.49
    rdom
    0.49
    ſhip
    0.49
     Faz
    0.48
    Activations Density 0.063%

    No Known Activations