© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5017
    Prev
    Next
    INDEX
    Explanations

    comma usage and occurrences in text

    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
    ciutto
    -0.62
    Filmografia
    -0.60
    homonymie
    -0.59
     فريبيس
    -0.58
    ))))
    -0.56
    verwijspagina
    -0.54
    ])))
    -0.54
    ]))
    -0.54
    лат
    -0.53
     lata
    -0.53
    POSITIVE LOGITS
    ousand
    0.82
    IndentedString
    0.73
     feroit
    0.69
     nemlig
    0.68
    ousands
    0.68
    rawQuery
    0.65
    MessageOf
    0.63
     tombé
    0.63
    BSD
    0.63
     auroit
    0.63
    Activations Density 0.091%

    No Known Activations