© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1958
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chere
    -0.44
     coming
    -0.39
     “
    -0.38
     brengen
    -0.38
    expandindo
    -0.38
     offered
    -0.38
    wegs
    -0.37
     M
    -0.37
     oferec
    -0.37
    ])),
    -0.37
    POSITIVE LOGITS
     Reſ
    0.94
     laſt
    0.92
     ſche
    0.90
     pleaſure
    0.90
     reaſon
    0.90
     ſta
    0.89
     ſtate
    0.88
    +#+#
    0.87
     houſe
    0.85
     BoxFit
    0.85
    Activations Density 0.734%

    No Known Activations