© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedural or methodological descriptions in scientific contexts

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

    Prepositions followed by abbreviations

    np_acts-logits-general · gemini-2.0-flash

    HFRS associated text

    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
     initComponents
    -0.59
    Ns
    -0.58
    Fs
    -0.54
    Gs
    -0.53
    Ds
    -0.52
    Ks
    -0.52
    A
    -0.51
    d
    -0.51
    Ls
    -0.51
    Hs
    -0.50
    POSITIVE LOGITS
    <bos>
    0.70
    mbggenerated
    0.68
    Telefax
    0.67
    zzleHttp
    0.64
    ]='\
    0.64
    ONESIA
    0.63
    хьтан
    0.62
    NewUrlParser
    0.61
    culoskeletal
    0.60
     anledning
    0.60
    Activations Density 0.702%

    No Known Activations