© 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. 4801
    Prev
    Next
    INDEX
    Explanations

    mentions of specific cultural or historical references related to preservation and recognition

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

    Follows punctuation and question words

    np_acts-logits-general · gemini-2.0-flash

    making, taking, putting

    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
     مشين
    -0.58
    guenos
    -0.57
     ویکی‌پدیای
    -0.57
     된
    -0.56
     副本
    -0.56
    trường
    -0.56
     صوتيه
    -0.54
    łóż
    -0.54
    Fazit
    -0.53
    #
    -0.53
    POSITIVE LOGITS
     Making
    1.43
    Making
    1.35
     Taking
    1.35
    Taking
    1.30
     Putting
    1.29
     Getting
    1.26
     Giving
    1.25
     Bringing
    1.24
     Doing
    1.24
    Getting
    1.22
    Activations Density 0.311%

    No Known Activations