© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 4661
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities and specific individuals

    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
     CreateTagHelper
    -0.72
    ConstraintMaker
    -0.67
    _);
    -0.48
    _));
    -0.47
     Biôgrafia
    -0.47
     Parenthood
    -0.46
    __)
    -0.43
    хьтан
    -0.42
     صوتيه
    -0.42
    _))
    -0.42
    POSITIVE LOGITS
    didReceive
    0.61
    csolódó
    0.60
    tagHelperRunner
    0.59
    loài
    0.58
    ={`/
    0.58
     youngest
    0.58
    CppMethod
    0.58
    ⓧ
    0.58
     thiệu
    0.58
    nivå
    0.58
    Activations Density 0.052%

    No Known Activations