© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12161
    Prev
    Next
    INDEX
    Explanations

    phrases indicating instances of action or state across various contexts

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

    Passive voice verbs following "is" or "was"

    np_acts-logits-general · gemini-2.0-flash

    state of completion

    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
    initComponents
    -0.51
    lectic
    -0.44
    eramente
    -0.44
     giusto
    -0.43
    unque
    -0.42
    olarmente
    -0.42
    CUL
    -0.42
    なるほど
    -0.42
    ilber
    -0.41
    BindView
    -0.41
    POSITIVE LOGITS
     done
    1.35
     accomplished
    1.32
     achieved
    1.31
     facilitated
    1.27
    achieved
    1.11
     possible
    1.10
     performed
    1.06
     handled
    1.03
     aided
    1.03
    done
    1.02
    Activations Density 0.634%

    No Known Activations