© 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
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 626
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the significance or essentiality of elements within a context

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

    part of a larger context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.57
    (&:
    -0.50
     >=",
    -0.50
     forceps
    -0.46
    uthorized
    -0.46
    zegovina
    -0.45
    unsplash
    -0.45
    angliski
    -0.44
     Exactos
    -0.44
    erees
    -0.44
    POSITIVE LOGITS
     HasFactory
    0.54
     Bestandteil
    0.51
     частью
    0.45
     часть
    0.41
    part
    0.41
     part
    0.40
    antMatchers
    0.39
    Часть
    0.39
    JvmStatic
    0.38
    的一部分
    0.37
    Activations Density 0.017%

    No Known Activations