© 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. 12619
    Prev
    Next
    INDEX
    Explanations

    concepts related to ministry and religious practices

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

    Follows URLs, asterisks, or certain numerics

    np_acts-logits-general · gemini-2.0-flash

    religious or technical terms

    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
    Innen
    -0.45
     expédi
    -0.44
     fabriquer
    -0.42
    百科
    -0.42
    점
    -0.42
    Personendaten
    -0.42
    ***
    -0.41
     Maddox
    -0.41
    ogy
    -0.40
     étanche
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.70
    RegressionTest
    0.66
    Moody
    0.59
    __":
    
    0.58
    ⤒
    0.57
     godly
    0.56
    TextHelper
    0.56
     Zion
    0.56
    ʖ
    0.55
     Experimental
    0.55
    Activations Density 0.084%

    No Known Activations