© 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. 6-GEMMASCOPE-RES-16K
    11. 14079
    Prev
    Next
    INDEX
    Explanations

    code-related constructs or statements in programming scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wicket
    -0.49
     GENE
    -0.49
    GENE
    -0.48
    ietf
    -0.46
    ativeness
    -0.46
     Colon
    -0.45
    testng
    -0.45
    geno
    -0.45
    ługa
    -0.45
     ContentValues
    -0.44
    POSITIVE LOGITS
    hasNext
    1.55
    EndContext
    1.53
    BackColor
    1.13
    AntiForgeryToken
    1.04
     CreateTagHelper
    1.02
    RegressionTest
    0.98
    ThroughAttribute
    0.91
    BuildContext
    0.91
     виправивши
    0.90
     TestBed
    0.85
    Activations Density 0.014%

    No Known Activations