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. 14106
    Prev
    Next
    INDEX
    Explanations

    elements related to social justice and advocacy for marginalized communities

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

    poverty or disadvantage

    np_acts-logits-general · gemini-2.0-flash

    poor and struggling people

    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
    RegistryLite
    -0.57
    itní
    -0.56
     expérimentés
    -0.49
    وش
    -0.49
     jsPsych
    -0.46
    instancetype
    -0.44
    ραν
    -0.44
    orah
    -0.44
    Compati
    -0.44
    ukkah
    -0.44
    POSITIVE LOGITS
     poor
    1.43
     poorer
    1.26
     poorest
    1.25
    poor
    1.21
    Poor
    1.08
     impoverished
    1.04
     POOR
    1.04
     Poor
    1.04
     disadvantaged
    1.01
     pobres
    0.95
    Activations Density 0.269%

    No Known Activations