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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 77497
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms related to biology and microbiology

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

    Pythagorean and Pythium

    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
    ChildScrollView
    -0.56
     referrerpolicy
    -0.46
    ilions
    -0.42
    liesslich
    -0.40
     топ
    -0.40
     étoit
    -0.40
     MutableLiveData
    -0.40
    preprint
    -0.39
    jata
    -0.38
    diano
    -0.38
    POSITIVE LOGITS
     Pythagorean
    1.26
     Pythagoras
    1.09
     Pythag
    1.04
    thag
    0.90
     Pit
    0.55
    adaptiveStyles
    0.52
     PIT
    0.51
     Py
    0.51
    +#+#
    0.50
    Py
    0.49
    Activations Density 0.010%

    No Known Activations