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. 5401
    Prev
    Next
    INDEX
    Explanations

    references to numbers and quantitative data

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

    "For the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    for the purpose/reason

    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
    encodeWith
    -0.61
    購入した
    -0.55
    ătă
    -0.51
     TestBed
    -0.50
    めでとう
    -0.48
    queles
    -0.48
    setAccessible
    -0.47
    }})
    -0.46
    getcwd
    -0.46
    開催
    -0.45
    POSITIVE LOGITS
     purposes
    1.84
     sake
    1.81
    purposes
    1.48
     purpose
    1.32
     Purposes
    1.31
    purpose
    1.14
     reasons
    1.10
    Purpose
    1.06
     Purpose
    0.98
     Sake
    0.98
    Activations Density 0.203%

    No Known Activations