© 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. 20-GEMMASCOPE-RES-16K
    11. 310
    Prev
    Next
    INDEX
    Explanations

    expressions related to actions and consequences involving planning or taking responsibility

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

    Word after "one", "it", "a", or similar short words

    np_acts-logits-general · gemini-2.0-flash

    "such"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     an
    -0.66
     unos
    -0.52
     awakeFromNib
    -0.51
     two
    -0.50
     some
    -0.48
    uncios
    -0.47
    Enllaços
    -0.46
    AddTagHelper
    -0.45
    ظه
    -0.45
    shafen
    -0.45
    POSITIVE LOGITS
     such
    0.81
    تقاوى
    0.80
    Such
    0.74
     solches
    0.74
    BeginContext
    0.72
     چنین
    0.69
     SUCH
    0.69
     Such
    0.68
     solch
    0.62
     ſuch
    0.61
    Activations Density 0.303%

    No Known Activations