Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 4435
    Prev
    Next
    INDEX
    Explanations

    technical terms or descriptions related to machinery, construction, or engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.54
    省市镇
    -0.52
    DataPropertyName
    -0.47
    TextSpan
    -0.47
    KeySpec
    -0.46
     يتيمه
    -0.45
    cherichia
    -0.43
    õi
    -0.43
    はじめに
    -0.42
     virgen
    -0.42
    POSITIVE LOGITS
     height
    2.03
     heights
    1.90
     Height
    1.74
     HEIGHT
    1.64
    height
    1.63
    Height
    1.57
     elevation
    1.57
     altura
    1.55
    heights
    1.53
    HEIGHT
    1.45
    Activations Density 0.522%

    No Known Activations