© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13895
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to physical phenomena and experiments

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

    Comes before prepositions or the word "effects"

    np_acts-logits-general · gemini-2.0-flash

    sources of effects and inaccuracies

    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
     promessa
    -0.52
    eseorang
    -0.51
    期刊论文
    -0.51
    довать
    -0.50
     facie
    -0.50
    __((
    -0.49
     tunggal
    -0.48
    setContentView
    -0.48
    bunda
    -0.48
     profesión
    -0.47
    POSITIVE LOGITS
     effects
    1.03
    effects
    0.88
     contributions
    0.83
     effets
    0.83
     inaccuracies
    0.78
     contribution
    0.76
     interactions
    0.76
     Effects
    0.76
     effect
    0.75
     unavoidable
    0.74
    Activations Density 2.143%

    No Known Activations