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. 25-GEMMASCOPE-RES-16K
    6. 10428
    Prev
    Next
    INDEX
    Explanations

    references to the Middle East and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basah
    -0.54
     torchvision
    -0.54
    )\}$
    -0.53
    Referencie
    -0.50
    ();*/
    -0.49
    });*/
    -0.48
     jadx
    -0.48
    IEM
    -0.47
    ']));
    -0.47
     Recap
    -0.46
    POSITIVE LOGITS
     Ages
    0.66
    principalTable
    0.65
     Aged
    0.65
    Aged
    0.64
    aged
    0.62
     aged
    0.62
     finger
    0.60
     ages
    0.58
     ground
    0.57
    PerformLayout
    0.56
    Activations Density 0.182%

    No Known Activations