© 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. 4101
    Prev
    Next
    INDEX
    Explanations

    references to literary works and authors

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

    that can be proper nouns

    np_acts-logits-general · gemini-2.0-flash

    Finnish place names and medical 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
    AutoScaleMode
    -0.60
    ks
    -0.48
    PropertyGroup
    -0.47
     CreateTagHelper
    -0.46
    *);
    -0.45
    KS
    -0.43
    AGR
    -0.40
    Troy
    -0.40
     ivelany
    -0.40
    
    -0.39
    POSITIVE LOGITS
     '\\;'
    0.67
    addCriterion
    0.61
    CROSSTALK
    0.57
     AssertionError
    0.56
     NDEBUG
    0.56
     BoxDecoration
    0.55
    PyErr
    0.55
     Branco
    0.53
     Pollut
    0.53
     RISERV
    0.53
    Activations Density 0.091%

    No Known Activations