© 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. 14253
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technical documentation and academic references

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

    Followed by "refer", "study", "paper", "blog", or "shop"

    np_acts-logits-general · gemini-2.0-flash

    academic, research, or specific places

    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
     الحره
    -0.80
    Hentet
    -0.75
     ſind
    -0.75
    τιά
    -0.72
     myſelf
    -0.70
    BeginContext
    -0.70
     ſever
    -0.70
     pleaſure
    -0.69
     faſt
    -0.68
     Reſ
    -0.68
    POSITIVE LOGITS
     that
    0.59
     are
    0.58
     were
    0.55
     مشين
    0.53
     which
    0.52
    ,
    0.46
     who
    0.44
     والتي
    0.43
     که
    0.43
     (
    0.43
    Activations Density 0.842%

    No Known Activations