© 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. 8787
    Prev
    Next
    INDEX
    Explanations

    complex scientific concepts and methodologies

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

    preceding research actions

    np_acts-logits-general · gemini-2.0-flash

    presenting or investigating findings

    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
     centaines
    -0.54
    enumi
    -0.51
    ReusableCell
    -0.49
    пиона
    -0.48
    ikuti
    -0.48
     dizaines
    -0.48
     milliers
    -0.47
    BackPressed
    -0.45
    GenerationType
    -0.44
     affaires
    -0.43
    POSITIVE LOGITS
     also
    1.23
     therefore
    1.08
     moreover
    0.99
    also
    0.96
     nevertheless
    0.93
     additionally
    0.93
     likewise
    0.91
     asimismo
    0.91
     также
    0.89
     alfo
    0.89
    Activations Density 0.690%

    No Known Activations