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. 12-GEMMASCOPE-RES-16K
    6. 14628
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to presentation or conveying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LogFactory
    -0.82
    XtraEditors
    -0.81
    
    -0.77
     الوطنيه
    -0.76
    jalá
    -0.76
    ankle
    -0.75
     OkHttpClient
    -0.75
     Dunlop
    -0.74
    ukone
    -0.71
    zieher
    -0.71
    POSITIVE LOGITS
     presents
    1.41
     presentations
    1.36
     Presents
    1.36
     presentation
    1.35
     presented
    1.34
     presenting
    1.31
     Presenting
    1.20
     Presentation
    1.19
     Presentations
    1.18
     PRESENT
    1.18
    Activations Density 0.088%

    No Known Activations