© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13122
    Prev
    Next
    INDEX
    Explanations

    terms related to considerations and factors that need to be taken into account, especially in discussions involving race and eligibility

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

    "into consideration" or "into account"

    np_acts-logits-general · gemini-2.0-flash

    consideration and account

    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
     esternos
    -0.67
    出版年
    -0.57
    \{\\
    -0.57
     henvisninger
    -0.57
     Италијани
    -0.55
     Monfieur
    -0.54
    antMatchers
    -0.54
     بيانات
    -0.54
     ſhall
    -0.53
     tenté
    -0.53
    POSITIVE LOGITS
     consideration
    0.87
     account
    0.75
    consider
    0.61
     Consideration
    0.60
     MainAxisSize
    0.58
    Datuak
    0.57
     consider
    0.56
    CONSIDER
    0.54
     CONSIDER
    0.53
    CompoundButton
    0.51
    Activations Density 0.138%

    No Known Activations