© 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. 24-GEMMASCOPE-RES-16K
    11. 4706
    Prev
    Next
    INDEX
    Explanations

    questions about career choices in educational contexts

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

    Study abroad programs

    np_acts-logits-general · gemini-2.0-flash

    study abroad programs

    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
     CreateTagHelper
    -0.60
    原始内容存档于
    -0.58
    IGraphics
    -0.57
     textStatus
    -0.53
    ométrique
    -0.49
    occhio
    -0.49
    Composable
    -0.48
     Orrell
    -0.47
    itattu
    -0.47
    Spoljašnje
    -0.47
    POSITIVE LOGITS
     exchange
    1.28
    exchange
    1.11
     Study
    1.09
    Exchange
    1.08
     study
    1.08
     Exchange
    1.04
     exchanges
    1.03
     abroad
    1.02
     Fulbright
    1.02
    Study
    1.01
    Activations Density 0.119%

    No Known Activations