Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13070
    Prev
    Next
    INDEX
    Explanations

    elements related to table structures and HTML coding

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

    Mathematical notation or small caps text

    np_acts-logits-general · gemini-2.0-flash

    small-caps formatting

    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
    PreferredItem
    -0.59
    ']],
    -0.52
     }))
    -0.49
    []{"
    -0.48
    __).
    -0.47
    ,:),
    -0.47
    asteroide
    -0.46
    AdapterFactory
    -0.46
     <
    -0.45
     }
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.84
     CreateTagHelper
    0.72
    tvguidetime
    0.65
    PyErr
    0.61
    DoubleQuotes
    0.61
     للمعارف
    0.61
     pinulongan
    0.61
    +:+
    0.61
    — 
    0.60
    MemoryWarning
    0.60
    Activations Density 0.103%

    No Known Activations