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. 16-GEMMASCOPE-RES-16K
    6. 12259
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to pharmacology and genetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or questions

    np_acts-logits-general · gemini-2.0-flash

    Q and A

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -1.10
    ReusableCell
    -0.98
     surla
    -0.91
     kasarigan
    -0.89
     tartalomajánló
    -0.87
    󠁮
    -0.86
    
    -0.86
     '\\;'
    -0.85
    Diwedd
    -0.84
    StructEnd
    -0.84
    POSITIVE LOGITS
    ↵
    0.54
    </em>
    0.51
    </strong>
    0.51
    </i>
    0.51
    </u>
    0.51
    ↵↵
    0.50
    </b>
    0.49
    </h2>
    0.46
     
    0.46
     Or
    0.44
    Activations Density 0.944%

    No Known Activations