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. 21-GEMMASCOPE-RES-16K
    6. 733
    Prev
    Next
    INDEX
    Explanations

    references to boards and board members in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    فحة
    -0.64
    ../../
    -0.61
    rious
    -0.59
     Picchu
    -0.58
    )))));
    -0.57
    cnbc
    -0.57
     Schna
    -0.56
    anément
    -0.56
    ']?>
    -0.55
    ră
    -0.54
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.79
    er
    0.77
     StatefulWidget
    0.74
    walks
    0.72
    room
    0.71
    member
    0.68
    walk
    0.68
     doInBackground
    0.66
     Member
    0.65
     member
    0.63
    Activations Density 0.047%

    No Known Activations