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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 932
    Prev
    Next
    INDEX
    Explanations

    specific HTML or coding syntax elements and comments in the text

    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
    SourceChecksum
    -1.06
    fjspx
    -0.87
    Vidite
    -0.77
    Personendaten
    -0.77
    InputTagHelper
    -0.77
     Roskov
    -0.73
    ThroughAttribute
    -0.72
    WriteBarrier
    -0.72
    ConstraintMaker
    -0.72
    richTextPanel
    -0.71
    POSITIVE LOGITS
    ictus
    0.59
    NotBe
    0.48
     nebu
    0.48
    ligo
    0.47
    pyl
    0.47
    PARATOR
    0.47
     defaultstate
    0.47
    diary
    0.46
    addOn
    0.46
    ikum
    0.46
    Activations Density 0.380%

    No Known Activations