© 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. 263
    Prev
    Next
    INDEX
    Explanations

    instances of formatting or structuring in text

    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
     nakalista
    -1.17
    LookAnd
    -1.12
     defaultstate
    -1.00
    +#+#
    -0.99
    BeginContext
    -0.96
    verwijspagina
    -0.96
    ViewFeatures
    -0.91
    UnitTesting
    -0.89
     Lightboxes
    -0.87
    Personendaten
    -0.85
    POSITIVE LOGITS
    )}.
    0.46
     }^{*}
    0.45
    ))*
    0.44
    RequestMapping
    0.44
    ))/
    0.44
    skat
    0.42
    '.
    0.42
     domain
    0.41
     zav
    0.41
     }?>
    0.41
    Activations Density 0.143%

    No Known Activations