© 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. 20-GEMMASCOPE-RES-16K
    11. 6887
    Prev
    Next
    INDEX
    Explanations

    references to concepts or notions related to 'ideas' and their attributes

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

    "idea" occurring in text

    np_acts-logits-general · gemini-2.0-flash

    idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yam
    -0.60
    s
    -0.58
    y
    -0.57
    px
    -0.54
    る
    -0.53
    </em>
    -0.51
    quiv
    -0.51
    heim
    -0.50
    らう
    -0.49
    l
    -0.49
    POSITIVE LOGITS
     ideas
    1.15
     IDEA
    1.13
    Ideas
    1.10
     Ideas
    1.09
    Idea
    1.02
    ideas
    1.01
     IDEAS
    1.00
     Idea
    0.93
    Демографія
    0.92
     inappropriés
    0.89
    Activations Density 0.080%

    No Known Activations