Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14011
    Prev
    Next
    INDEX
    Explanations

    concepts related to depth and understanding, particularly in the context of analytical insights

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

    associated with the concept of depth

    np_acts-logits-general · gemini-2.0-flash

    depth and penetration

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ImageContext
    -0.63
     informée
    -0.59
    orianCalendar
    -0.53
     '{@
    -0.52
     kasarigan
    -0.52
    ⟬
    -0.52
     plufieurs
    -0.51
    ADT
    -0.51
     onCreateView
    -0.51
     становника
    -0.50
    POSITIVE LOGITS
     deep
    0.93
     deeper
    0.91
     depth
    0.81
    deep
    0.80
    depth
    0.76
     depths
    0.73
     Deeper
    0.72
     deeply
    0.71
    Deep
    0.70
     DEPTH
    0.69
    Activations Density 0.374%

    No Known Activations