© 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. 2559
    Prev
    Next
    INDEX
    Explanations

    phrases related to needs assessment and research proposals

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

    Areas for improvement or further research

    np_acts-logits-general · gemini-2.0-flash

    identifying areas for improvement

    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
    esc
    -0.51
     calculators
    -0.50
     Comput
    -0.49
    InstrumentedTest
    -0.47
     Meksiku
    -0.46
    iedades
    -0.46
    FirebaseDatabase
    -0.46
    scalatest
    -0.46
     TextAlign
    -0.46
    calcul
    -0.45
    POSITIVE LOGITS
     deficiencies
    1.37
     areas
    1.37
     weaknesses
    1.36
     improvement
    1.35
     improvements
    1.31
     gaps
    1.31
    Areas
    1.26
    areas
    1.25
     shortcomings
    1.24
     Improvement
    1.22
    Activations Density 0.366%

    No Known Activations