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. 17-GEMMASCOPE-RES-16K
    6. 13317
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a lack or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laquelle
    -0.61
     متعلقه
    -0.60
     suivantes
    -0.56
    seamnă
    -0.56
     duquel
    -0.55
     ciascuno
    -0.55
     betweenstory
    -0.54
     quelqu
    -0.53
    ագրություններ
    -0.52
     saites
    -0.52
    POSITIVE LOGITS
     no
    0.83
     real
    0.76
     other
    0.73
     more
    0.73
     significant
    0.70
     idea
    0.68
     extra
    0.68
     further
    0.67
    igno
    0.66
     additional
    0.64
    Activations Density 0.187%

    No Known Activations