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. 1-GEMMASCOPE-RES-16K
    6. 9500
    Prev
    Next
    INDEX
    Explanations

    terms related to artistic exhibitions and creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sogni
    -0.47
    QObject
    -0.41
    g
    -0.40
     l
    -0.39
     Gaff
    -0.39
     emerging
    -0.39
    j
    -0.39
    Expecting
    -0.39
    pel
    -0.39
     rangs
    -0.39
    POSITIVE LOGITS
    ThroughAttribute
    0.95
    tagHelperRunner
    0.75
    setVerticalGroup
    0.73
     itſelf
    0.72
     initComponents
    0.71
    intervento
    0.71
     createSlice
    0.71
     utafitiHapana
    0.71
    [];
    
    0.70
    AfterClass
    0.69
    Activations Density 0.090%

    No Known Activations