© 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. 4-GEMMASCOPE-RES-16K
    6. 2957
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the composition or material of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jegyzetek
    -0.71
    WebControls
    -0.69
    IBAction
    -0.63
     QName
    -0.61
    WaitGroup
    -0.60
     JpaRepository
    -0.59
    Смотрите
    -0.59
     AssemblyTitle
    -0.59
     intStringLen
    -0.59
    }{*}{
    -0.58
    POSITIVE LOGITS
     terbuat
    0.77
    SOUNDBITE
    0.63
    made
    0.62
     pure
    0.61
     gemaakt
    0.61
     made
    0.60
     wykonane
    0.60
     comprised
    0.60
     materiali
    0.60
    materials
    0.59
    Activations Density 0.318%

    No Known Activations