© 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. 18-GEMMASCOPE-RES-16K
    11. 1713
    Prev
    Next
    INDEX
    Explanations

    specific names and proper nouns

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

    ending in "tt", "ss", "ARR", "Azz"

    np_acts-logits-general · gemini-2.0-flash

    Azz, ARR, Ott, mann

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ​​
    -0.71
    actionBar
    -0.57
    位
    -0.56
    ❷
    -0.56
    рои
    -0.55
    望
    -0.55
     Bourgoin
    -0.55
    도
    -0.54
    érieurs
    -0.54
    en
    -0.54
    POSITIVE LOGITS
     Coss
    0.91
     Azz
    0.91
    CrossRef
    0.90
    Yess
    0.86
     Utt
    0.85
     OSS
    0.84
    edd
    0.84
    MethodManager
    0.82
    Ayy
    0.82
     Genn
    0.80
    Activations Density 0.749%

    No Known Activations