© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14301
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and library imports related to data manipulation and scientific computing

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

    Python and NumPy code

    np_acts-logits-general · gemini-2.0-flash

    numpy and python code

    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
    GraphicsUnit
    -0.40
    UpInside
    -0.39
    ..\
    -0.38
    TextWatcher
    -0.38
     llan
    -0.36
    PullParser
    -0.36
    ]=="
    -0.35
    }:{
    -0.35
     belongs
    -0.35
     kaarangay
    -0.34
    POSITIVE LOGITS
     numpy
    1.11
    numpy
    0.80
    GEBURTSDATUM
    0.69
     informée
    0.68
     pylab
    0.66
    npy
    0.63
     scipy
    0.61
    setVerticalGroup
    0.61
    cipy
    0.61
    addPreferredGap
    0.61
    Activations Density 0.149%

    No Known Activations