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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 14126
    Prev
    Next
    INDEX
    Explanations

    references to speakers or audio playback devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝐳
    -0.72
     coû
    -0.68
    fits
    -0.61
     đốc
    -0.61
    ไตล์
    -0.60
     ';
    
    -0.59
    ')),
    -0.58
    "]));
    -0.58
    ely
    -0.57
     CET
    -0.57
    POSITIVE LOGITS
     speaker
    2.22
     Speaker
    2.19
    Speaker
    2.11
     Speakers
    2.03
     speakers
    2.02
    speaker
    2.02
    SPEAKER
    1.94
     SPEAKER
    1.91
    speakers
    1.90
    Speakers
    1.73
    Activations Density 0.039%

    No Known Activations