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. 20-GEMMASCOPE-RES-16K
    6. 1058
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions that emphasize examples or specific instances

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

    "such"

    np_acts-logits-general · gemini-2.0-flash

    such as / such a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alguno
    -0.52
    ValueStyle
    -0.51
    __()
    -0.50
     algún
    -0.50
    *
    -0.50
    ​
    -0.49
     algum
    -0.48
     próprios
    -0.48
     alguna
    -0.48
     /\.
    -0.47
    POSITIVE LOGITS
    OrNil
    0.83
     рода
    0.83
     собі
    0.80
     вот
    0.74
     **/
    
    0.71
     thing
    0.68
    yntaxException
    0.67
    maschinen
    0.67
    الدراسه
    0.67
    maar
    0.66
    Activations Density 0.154%

    No Known Activations