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. 7-GEMMASCOPE-RES-16K
    6. 11626
    Prev
    Next
    INDEX
    Explanations

    references to news media outlets and television broadcasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PrototypeOf
    -0.75
     مواليد
    -0.70
    fjspx
    -0.68
    DeleteBehavior
    -0.68
     estimés
    -0.66
     protoimpl
    -0.64
    WriteTagHelper
    -0.63
    uxxxx
    -0.60
    moine
    -0.59
    DebuggerNonUser
    -0.59
    POSITIVE LOGITS
     television
    1.12
     Television
    1.05
     televis
    0.96
     TV
    0.94
    television
    0.91
    Television
    0.91
     televisión
    0.86
     televisi
    0.83
     televiz
    0.82
    TV
    0.81
    Activations Density 0.167%

    No Known Activations