© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 108034
    Prev
    Next
    INDEX
    Explanations

    the presence of the word 'a' and its variations in different contexts

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

    after a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Vereinigte
    -0.40
     nakalista
    -0.38
     δή
    -0.36
    JNIEnv
    -0.35
    plaat
    -0.35
    ("}");
    -0.34
    دانشنامهٔ
    -0.34
    JRadioButton
    -0.34
     Osna
    -0.34
    =$?
    -0.33
    POSITIVE LOGITS
    Após
    0.87
     After
    0.87
    After
    0.82
     fter
    0.81
     Após
    0.81
     Etter
    0.77
    after
    0.75
     after
    0.74
    andafter
    0.74
    Etter
    0.74
    Activations Density 0.008%

    No Known Activations