© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6654
    Prev
    Next
    INDEX
    Explanations

    lines and comments related to code structure or syntax in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.70
    __*/
    -0.59
    ]")]
    -0.57
     صوتيه
    -0.56
     pungkas
    -0.54
    __':
    
    -0.52
    })`
    -0.52
    ArgsConstructor
    -0.51
    viewDidLoad
    -0.51
    元年
    -0.48
    POSITIVE LOGITS
    帖最后由
    0.71
    NewUrlParser
    0.69
    issauga
    0.64
    ervlak
    0.59
     AssemblyCompany
    0.58
     pneumoniae
    0.58
     langu
    0.57
    BagConstraints
    0.57
     متعلقه
    0.56
     Ceux
    0.56
    Activations Density 0.118%

    No Known Activations