© 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. 3544
    Prev
    Next
    INDEX
    Explanations

    terms related to parenting and parental involvement

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

    "parent" or related terms

    np_acts-logits-general · gemini-2.0-flash

    parent portal, project, guidance

    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
     /\.(
    -0.83
     nahilalakip
    -0.81
    httphttps
    -0.80
     Réponses
    -0.77
    ]),
    -0.76
     kaarangay
    -0.75
    Revenir
    -0.72
    NameInMap
    -0.71
     AssemblyCompany
    -0.70
    nologies
    -0.69
    POSITIVE LOGITS
    hetically
    0.85
     parents
    0.78
    PARENT
    0.76
    hetic
    0.74
    Parents
    0.73
     Parents
    0.71
     PARENTS
    0.69
    heses
    0.67
    parent
    0.67
     PARENT
    0.66
    Activations Density 0.052%

    No Known Activations