© 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. 5-GEMMASCOPE-RES-16K
    11. 8104
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to system setup and initialization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     x
    -0.55
    ,
    -0.45
    sp
    -0.44
    off
    -0.42
    art
    -0.42
     w
    -0.41
     off
    -0.41
    ats
    -0.40
    vi
    -0.40
     po
    -0.40
    POSITIVE LOGITS
     متعلقه
    1.04
     preparations
    1.03
    ^(@)
    1.02
     myſelf
    0.96
     Efq
    0.94
     ModelExpression
    0.94
     Preparations
    0.94
    +#+#
    0.93
     houſe
    0.92
    Подготовка
    0.92
    Activations Density 0.429%

    No Known Activations