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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15273
    Prev
    Next
    INDEX
    Explanations

    narratives involving transformation or significant change in characters or situations

    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
     picioare
    -0.53
     fatos
    -0.47
     geslacht
    -0.46
    gants
    -0.46
     représentants
    -0.46
     partielle
    -0.46
    )))));
    -0.46
     MaterialApp
    -0.45
     chrétien
    -0.45
     chồng
    -0.45
    POSITIVE LOGITS
     titular
    0.64
     aku
    0.59
     متعلقه
    0.59
    amur
    0.59
    tagens
    0.59
    waran
    0.58
     rival
    0.58
    >>()
    0.57
     насељу
    0.57
     Pri
    0.56
    Activations Density 0.489%

    No Known Activations