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. 15238
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to additions or increments

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

    "add" and its variations

    np_acts-logits-general · gemini-2.0-flash

    add commands and phrases

    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
    																										
    -0.59
    stdc
    -0.55
    }<\
    -0.54
    ized
    -0.53
     particulières
    -0.52
    ensores
    -0.52
    izados
    -0.51
    Ỉ
    -0.50
     gantung
    -0.50
    voorbeeld
    -0.50
    POSITIVE LOGITS
     add
    1.16
     Adds
    1.12
     adds
    1.11
     adding
    1.07
     Adding
    1.06
    Adding
    1.03
    Adds
    1.02
     hinzu
    1.00
     Add
    0.99
     ADD
    0.96
    Activations Density 0.155%

    No Known Activations