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. 20-GEMMASCOPE-RES-16K
    6. 10356
    Prev
    Next
    INDEX
    Explanations

    sections of code or programming-related references

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

    Non-English text and code snippets

    np_acts-logits-general · gemini-2.0-flash

    non-Latin scripts and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.97
     raiſ
    -0.93
     houſe
    -0.93
     purpoſe
    -0.92
     Jefus
    -0.90
     cauſe
    -0.89
     ſte
    -0.85
     miſ
    -0.84
     ſur
    -0.84
     fernández
    -0.84
    POSITIVE LOGITS
    ")));
    
    0.49
    ()))
    
    0.45
     '))
    0.44
    )))
    
    0.44
    ')))
    0.43
    )));
    
    0.43
    }}}
    
    0.42
    +");
    0.42
    }")
    
    0.41
    ')));
    0.41
    Activations Density 0.003%

    No Known Activations