© 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. 13950
    Prev
    Next
    INDEX
    Explanations

    intensifiers or descriptors of depth and significance

    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
     Roskov
    -0.85
    MessageTagHelper
    -0.81
     Normdatei
    -0.79
    Kontrola
    -0.78
    queryInterface
    -0.77
    oa̍t
    -0.76
     ContentValues
    -0.76
    DebuggerNonUser
    -0.75
     StringTokenizer
    -0.74
    原始内容存档于
    -0.74
    POSITIVE LOGITS
     deep
    3.72
     Deep
    3.29
    deep
    3.23
    Deep
    3.18
     DEEP
    3.16
    DEEP
    2.81
     deeper
    2.63
     deepest
    2.62
     deeply
    2.24
     Deeper
    2.20
    Activations Density 0.046%

    No Known Activations