© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2968
    Prev
    Next
    INDEX
    Explanations

    terms related to permissions and errors in a technical context

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

    German language or script

    np_acts-logits-general · gemini-2.0-flash

    German prefixes plus completions

    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
     varandra
    -0.58
     būtų
    -0.57
     veiks
    -0.56
     stället
    -0.51
     noemen
    -0.49
     žem
    -0.49
    řízení
    -0.48
     geldt
    -0.48
     bezit
    -0.48
     genieten
    -0.48
    POSITIVE LOGITS
     الحره
    0.65
    clable
    0.60
    ()]
    0.58
    ()].
    0.57
    Hozzáférés
    0.54
    原始内容存档于
    0.54
    WebElementEntity
    0.54
    helf
    0.53
    falls
    0.53
    llary
    0.53
    Activations Density 0.021%

    No Known Activations