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. 13715
    Prev
    Next
    INDEX
    Explanations

    references to individuals and relationships

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

    Initials followed by a short suffix

    np_acts-logits-general · gemini-2.0-flash

    ending in 'an' or 'lan'

    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
     Bumble
    -0.71
     Bort
    -0.61
     Salom
    -0.56
     Reggie
    -0.56
     Cabello
    -0.55
    ometry
    -0.55
     Julius
    -0.55
     Gum
    -0.54
    CORD
    -0.54
     Perch
    -0.54
    POSITIVE LOGITS
    BAN
    1.11
    ban
    1.11
     Alan
    1.06
     BAN
    1.06
    LAN
    1.03
    Ban
    1.03
    lan
    1.02
    alan
    1.01
    Alan
    1.01
     lan
    0.99
    Activations Density 0.591%

    No Known Activations