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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15452
    Prev
    Next
    INDEX
    Explanations

    conditional statements relating to responsibility and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tslint
    -0.80
     itſelf
    -0.69
    sidemargin
    -0.68
    terness
    -0.68
    发表于
    -0.66
    ГЛА
    -0.65
    NOPQRST
    -0.64
    IndentedString
    -0.64
     pleaſure
    -0.63
     المعيارى
    -0.62
    POSITIVE LOGITS
    すれば
    0.72
    れば
    0.55
     megfe
    0.51
    せば
    0.50
    えば
    0.48
     ajutor
    0.47
     saja
    0.46
    нибудь
    0.45
    Simply
    0.45
     suitably
    0.45
    Activations Density 0.467%

    No Known Activations