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. 2-GEMMASCOPE-RES-16K
    6. 15964
    Prev
    Next
    INDEX
    Explanations

    the concept of making a significant difference in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.69
    #+#
    -0.64
    verwijspagina
    -0.62
    ynch
    -0.60
     المعيارى
    -0.58
    ForRow
    -0.57
    CodedInputStream
    -0.56
    Differences
    -0.55
     Bourne
    -0.54
    featureID
    -0.53
    POSITIVE LOGITS
    __':
    0.70
    initComponents
    0.69
     مشين
    0.68
    izr
    0.68
     discharge
    0.68
    RegressionTest
    0.66
     LIFT
    0.66
     Vikipedi
    0.64
     discharging
    0.64
     Discharge
    0.62
    Activations Density 0.058%

    No Known Activations