© 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. 18-GEMMASCOPE-RES-16K
    11. 8336
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to child safety and health issues

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

    children or young people

    np_acts-logits-general · gemini-2.0-flash

    young children and adolescents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.61
     utafitiHapana
    -0.57
     EconPapers
    -0.55
     suaminya
    -0.53
    коменду
    -0.49
    Beijo
    -0.49
    alamualaikum
    -0.48
    alnız
    -0.47
     متعلقه
    -0.46
    ErrUnexpectedEOF
    -0.46
    POSITIVE LOGITS
     children
    2.39
     kids
    2.34
     young
    2.11
     child
    2.06
     youngsters
    2.00
    kids
    1.95
    children
    1.93
     kid
    1.92
    Kids
    1.88
     Kids
    1.87
    Activations Density 0.515%

    No Known Activations