© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    programming commands and file management terms

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

    Comes before "and" or "you," indicating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    and starting

    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
    ứng
    -0.48
     arquitect
    -0.47
    MenuInflater
    -0.45
     --}}
    -0.42
    cuno
    -0.42
     Lordships
    -0.42
    AndEndTag
    -0.40
    hisattva
    -0.40
    それとも
    -0.40
    Nonnull
    -0.39
    POSITIVE LOGITS
     voila
    1.42
     voilà
    1.37
     Done
    1.33
    Done
    1.22
    Voila
    1.18
     done
    1.11
     DONE
    1.09
     Voilà
    1.08
    done
    1.07
     boom
    1.01
    Activations Density 0.378%

    No Known Activations