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. 24-GEMMASCOPE-RES-16K
    6. 8118
    Prev
    Next
    INDEX
    Explanations

    references to young individuals or groups in various contexts

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

    "young" preceding a demographic

    np_acts-logits-general · gemini-2.0-flash

    young people and their associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     young
    -0.82
     jeune
    -0.76
    young
    -0.74
     giovani
    -0.73
    UnsafeEnabled
    -0.72
     autorytatywna
    -0.72
     giovane
    -0.72
    Young
    -0.68
     jonge
    -0.68
     transfieras
    -0.67
    POSITIVE LOGITS
    sters
    0.85
    blood
    0.83
    stown
    0.68
    STERS
    0.67
    ster
    0.67
    ish
    0.64
    eſt
    0.63
     guns
    0.62
    lings
    0.61
     minds
    0.60
    Activations Density 0.068%

    No Known Activations