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. 10452
    Prev
    Next
    INDEX
    Explanations

    words and phrases focused on personal interactions and relationships

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

    Misspellings or non-standard spellings

    np_acts-logits-general · gemini-2.0-flash

    misspellings and abbreviations

    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
    CloseOperation
    -1.30
    enumi
    -1.26
     iſt
    -1.06
    tagHelperRunner
    -1.06
     ―――――
    -1.01
     pinulongan
    -1.00
    MessageState
    -0.99
     вікісторінку
    -0.98
     كومونز
    -0.98
     الحره
    -0.96
    POSITIVE LOGITS
    </strong>
    0.75
    n
    0.65
    </em>
    0.65
    <bos>
    0.63
    ir
    0.62
    out
    0.61
    <strong>
    0.60
    r
    0.60
      
    0.57
    ly
    0.56
    Activations Density 0.479%

    No Known Activations