© 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 EvalsExportsAPI 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. 1265
    Prev
    Next
    INDEX
    Explanations

    URLs and data attributes related to multimedia content

    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
    setVerticalGroup
    -0.90
    UserScript
    -0.85
     CreateTagHelper
    -0.76
     Anſ
    -0.72
    adaptiveStyles
    -0.72
    UseVisualStyle
    -0.71
    PreferredItem
    -0.69
    FunctionFlags
    -0.69
     Rhodesia
    -0.68
     morire
    -0.67
    POSITIVE LOGITS
    Παραπομπές
    0.54
    +#+#
    0.53
     all
    0.48
     GenerationType
    0.46
    columbia
    0.46
    سمبر
    0.45
    tuigen
    0.45
    geving
    0.45
     a
    0.44
     lenker
    0.44
    Activations Density 0.607%

    No Known Activations