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. 5895
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration or teamwork

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

    "We" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    We decided

    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
    ScopeManager
    -0.65
    loem
    -0.63
    GraphicsUnit
    -0.60
    出版年
    -0.56
    ftagPool
    -0.56
    willReturn
    -0.53
    InputBorder
    -0.53
     oprot
    -0.51
    今日も
    -0.51
     فريبيس
    -0.49
    POSITIVE LOGITS
     wanted
    1.32
    wanted
    1.12
     decided
    1.03
     Wanted
    1.00
    Wanted
    0.99
     quería
    0.90
     chose
    0.88
     øns
    0.88
     Decided
    0.88
     hoped
    0.87
    Activations Density 0.255%

    No Known Activations