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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5844
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate origins or sources

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

    "from"

    np_acts-logits-general · gemini-2.0-flash

    origin or starting point

    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
     rospy
    -0.57
    깐
    -0.56
     они
    -0.52
     bezeichneter
    -0.52
    anteed
    -0.47
     він
    -0.46
    OrUpdate
    -0.46
    وء
    -0.46
    wählen
    -0.46
     вони
    -0.43
    POSITIVE LOGITS
     afar
    1.39
     within
    1.24
    within
    1.18
     whence
    1.17
     across
    1.17
     scratch
    1.12
     elsewhere
    1.08
     abroad
    1.04
     inside
    1.02
     anywhere
    1.02
    Activations Density 0.278%

    No Known Activations