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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 15115
    Prev
    Next
    INDEX
    Explanations

    ellipses or pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ·
    -1.00
    "):
    
    -0.94
     InputDecoration
    -0.93
     ();
    
    -0.90
    %");
    -0.84
     ());
    -0.79
     :</
    -0.78
    )");
    
    -0.78
     〈
    -0.76
    '):
    
    -0.75
    POSITIVE LOGITS
    ...
    1.46
    …
    1.40
    ..
    1.08
    ....
    1.07
    …’
    0.98
    、、、
    0.98
    ….
    0.97
    .....
    0.93
    …..
    0.92
    ..!
    0.91
    Activations Density 0.332%

    No Known Activations