© 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. 9-GEMMASCOPE-RES-131K
    11. 14062
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific accented vowels or special characters

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

    à, ò, è, à la

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.48
    SequentialGroup
    -0.43
    detach
    -0.41
     (
    -0.40
     
    -0.40
    lazy
    -0.40
    Lazy
    -0.38
     MonoBehaviour
    -0.37
     vider
    -0.37
     (__
    -0.37
    POSITIVE LOGITS
    à
    1.43
    ò
    1.15
    è
    1.13
    À
    1.05
    ì
    1.04
    ù
    1.00
    ̀
    0.88
     à
    0.85
    lè
    0.84
    rè
    0.83
    Activations Density 0.002%

    No Known Activations