© 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. 38-GEMMASCOPE-RES-16K
    11. 7389
    Prev
    Next
    INDEX
    Explanations

    terms related to synaptic plasticity, specifically long-term depression (LTD) and calcium signaling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.46
    Билгалдахарш
    -0.42
    uría
    -0.40
    EDEFAULT
    -0.40
    ultades
    -0.39
    塙
    -0.39
    ArgsConstructor
    -0.37
     Achtung
    -0.37
    essoal
    -0.36
     argint
    -0.36
    POSITIVE LOGITS
     synaptic
    0.59
     dendritic
    0.56
     circuit
    0.55
     excit
    0.54
     firing
    0.54
     gluta
    0.51
     dend
    0.50
     basket
    0.50
     pres
    0.50
     circuitos
    0.49
    Activations Density 1.240%

    No Known Activations