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. 4568
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to research methodology

    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
     onCancelled
    -0.82
    
    -0.73
    webElementGuid
    -0.71
     ProtoMessage
    -0.70
    adaptiveStyles
    -0.70
    zzleHttp
    -0.69
    PerformLayout
    -0.68
    rungsseite
    -0.68
     通販
    -0.66
    __":
    
    -0.65
    POSITIVE LOGITS
    一樣
    0.56
    一样
    0.55
    同様に
    0.55
    Зри
    0.50
    Hrsg
    0.48
    一样的
    0.47
    AndEndTag
    0.46
    ötzlich
    0.46
     serupa
    0.45
    行政区划
    0.44
    Activations Density 0.565%

    No Known Activations