Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 12801
    Prev
    Next
    INDEX
    Explanations

    phrases related to company policies and claims procedures

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

    Following a company or entity name

    np_acts-logits-general · gemini-2.0-flash

    not charge or require

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.50
     sleepless
    -0.49
    ::_('
    -0.45
     Brought
    -0.45
     leads
    -0.44
     sojourn
    -0.43
     trasc
    -0.43
    kuuta
    -0.43
    CloseOperation
    -0.42
    Bibliograf
    -0.42
    POSITIVE LOGITS
     charge
    1.17
     charging
    1.10
     require
    0.96
     Charge
    0.95
    Charging
    0.94
    Charge
    0.94
    charge
    0.93
     Charging
    0.93
     charged
    0.92
     Require
    0.89
    Activations Density 0.393%

    No Known Activations