© 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. 22-GEMMASCOPE-RES-16K
    6. 3720
    Prev
    Next
    INDEX
    Explanations

    references to error handling and processing outcomes in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Id" followed by a period

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ").
    -1.29
    ').
    -1.20
    "].
    -1.16
    ”).
    -1.06
    ")->
    -1.05
    」。
    -1.03
    ')->
    -1.03
    `).
    -1.00
    )].
    -1.00
    ";
    
    -0.99
    POSITIVE LOGITS
    >')
    0.72
    }`)
    0.71
    .")
    0.67
    '")
    0.65
    ']")
    0.65
    .')
    0.64
    .)}
    0.63
     {})
    0.62
    afficheront
    0.60
    }))
    
    0.60
    Activations Density 0.359%

    No Known Activations