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. 13041
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to growth or development

    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
     alertDialog
    -0.68
     }^{[
    -0.64
     [*]
    -0.62
    ques
    -0.58
    nimo
    -0.58
    inians
    -0.57
    uci
    -0.56
     hinted
    -0.56
                    
    -0.55
     tinnitus
    -0.55
    POSITIVE LOGITS
     GROW
    2.43
     grow
    2.41
     Grow
    2.30
     grows
    2.30
    grow
    2.30
     growing
    2.26
    GROW
    2.22
    Grow
    2.19
    growing
    2.11
     Growing
    2.06
    Activations Density 0.052%

    No Known Activations