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. 17-GEMMASCOPE-RES-16K
    6. 9072
    Prev
    Next
    INDEX
    Explanations

    financial and fiscal reporting details

    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
    featureID
    -0.61
    #+#
    -0.53
    TintMode
    -0.52
     CURIAM
    -0.50
     iprot
    -0.49
    $_['
    -0.47
     oprot
    -0.47
    defn
    -0.47
    mson
    -0.46
    webElementXpaths
    -0.45
    POSITIVE LOGITS
     fiscal
    1.03
     period
    1.01
    period
    0.88
     Fiscal
    0.87
    fiscal
    0.84
     perioden
    0.83
     periode
    0.83
    Fiscal
    0.82
     Period
    0.82
     FISCAL
    0.81
    Activations Density 0.278%

    No Known Activations