© 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. 9512
    Prev
    Next
    INDEX
    Explanations

    terms related to methodologies and processes in scientific or engineering contexts

    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
    Sitting
    -0.58
    ContextHolder
    -0.55
     Heading
    -0.55
     Promotes
    -0.54
     Spreading
    -0.54
     Talking
    -0.54
     Tells
    -0.54
     Gets
    -0.53
    istik
    -0.53
     heading
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.91
    +#+#
    0.84
     computing
    0.83
     calculating
    0.80
     nahilalakip
    0.79
     constructing
    0.77
     approximating
    0.76
     determining
    0.76
     deriving
    0.76
     performing
    0.75
    Activations Density 1.545%

    No Known Activations