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. 9-GEMMASCOPE-RES-16K
    6. 15790
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.86
    AnchorStyles
    -0.84
    脚注の使い方
    -0.83
    DockStyle
    -0.82
    basicConfig
    -0.78
     '\\;'
    -0.77
    initComponents
    -0.76
    bewerken
    -0.74
    
    -0.72
    CppMethod
    -0.72
    POSITIVE LOGITS
     pulumi
    0.47
     ffilm
    0.45
     Signalez
    0.41
    "))
    0.41
    стра
    0.40
    ";
    
    0.39
     vorbere
    0.39
     familiar
    0.38
    ostro
    0.38
    lan
    0.37
    Activations Density 0.049%

    No Known Activations