© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10198
    Prev
    Next
    INDEX
    Explanations

    financial metrics and statistics, particularly percentages and numerical data

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

    Numbers followed by a percentage or basis points

    np_acts-logits-general · gemini-2.0-flash

    percentages and rates

    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
     hvit
    -0.63
     صوتيه
    -0.58
    ظيم
    -0.55
     ogóle
    -0.51
     humains
    -0.50
     Thickness
    -0.50
     hvid
    -0.50
     voks
    -0.49
     AssemblyProduct
    -0.48
    ]--;
    -0.48
    POSITIVE LOGITS
     basis
    0.77
     percentage
    0.73
     points
    0.72
    %/
    0.67
    XmlAccessorType
    0.64
     []:
    0.61
     point
    0.60
     ppt
    0.60
    BufferException
    0.60
    basis
    0.58
    Activations Density 0.187%

    No Known Activations