© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14720
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or the need for further investigation

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

    "The" preceding abstract nouns or concepts

    np_acts-logits-general · gemini-2.0-flash

    the + idea / possibility / fact / issue / need

    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
    }></
    -0.63
    GeneratedCode
    -0.61
     beginnetje
    -0.61
     venons
    -0.58
    Portale
    -0.58
     prefent
    -0.55
     reft
    -0.55
     fleste
    -0.54
     réussite
    -0.52
     AssemblyCompany
    -0.52
    POSITIVE LOGITS
     idea
    1.67
     possibility
    1.59
     notion
    1.54
     fact
    1.52
    possibility
    1.22
    idée
    1.18
     need
    1.15
     ideia
    1.14
    idea
    1.13
     assumption
    1.11
    Activations Density 0.507%

    No Known Activations