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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8451
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to measurement and quantification

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

    "measure" and measurements

    np_acts-logits-general · gemini-2.0-flash

    measure, measurement, or measuring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    ContentAsync
    -0.75
    Kjelder
    -0.73
     للاسماء
    -0.71
     Савезне
    -0.71
     doInBackground
    -0.70
     BeautifulSoup
    -0.63
    SequentialGroup
    -0.63
    RTEX
    -0.62
    posedge
    -0.61
     resourceCulture
    -0.61
    POSITIVE LOGITS
     Measures
    0.74
     measures
    0.69
    Measures
    0.67
    measures
    0.64
    MEAS
    0.61
    asures
    0.61
    cura
    0.61
     Measurements
    0.60
    providedIn
    0.59
    menta
    0.58
    Activations Density 0.107%

    No Known Activations