© 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. 13078
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their experiences or actions

    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
    DockStyle
    -0.84
     صوتيه
    -0.70
    $_['
    -0.69
     оригіналу
    -0.64
     ProtoMessage
    -0.62
    InjectAttribute
    -0.61
    fjspx
    -0.61
    WithMany
    -0.58
    understanding
    -0.58
    esgue
    -0.58
    POSITIVE LOGITS
     know
    2.36
    know
    1.66
     knows
    1.57
     Know
    1.37
    Know
    1.31
     KNOW
    1.19
    knows
    1.09
    KNOW
    1.01
     wissen
    0.97
     kno
    0.97
    Activations Density 0.306%

    No Known Activations