© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 923
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to evaluating claims and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.88
    MemoryWarning
    -0.74
    SBATCH
    -0.73
    expandindo
    -0.70
     Normdatei
    -0.66
     resourceCulture
    -0.65
    تقاوى
    -0.65
    AndroidJUnit
    -0.62
    featureID
    -0.60
     >=",
    -0.60
    POSITIVE LOGITS
     substantive
    1.25
     actual
    1.17
     substance
    1.14
     content
    1.12
    content
    1.00
     eigentlichen
    0.98
    actual
    0.98
    Actual
    0.96
     tatsäch
    0.92
    中身
    0.92
    Activations Density 0.759%

    No Known Activations