© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 2285
    Prev
    Next
    INDEX
    Explanations

    Java code structure elements, such as interfaces and methods

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     HasFactory
    -0.62
    stdc
    -0.56
    ictwo
    -0.55
    alnız
    -0.52
    ΕΛ
    -0.52
     ElementRef
    -0.51
     serializers
    -0.51
    structors
    -0.49
    UpInside
    -0.49
    athyroid
    -0.49
    POSITIVE LOGITS
    abstractmethod
    1.06
    OGND
    0.66
    原始内容存档于
    0.64
     Pristupljeno
    0.62
     Normdatei
    0.59
    下载附件
    0.58
    InjectAttribute
    0.58
    ;\
    0.57
    ();)
    0.56
    ]]);
    0.56
    Activations Density 0.061%

    No Known Activations