© 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. 2-GEMMASCOPE-RES-16K
    6. 1867
    Prev
    Next
    INDEX
    Explanations

    instances of the word "type" and its variations, indicating a focus on categorization

    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
    UnsafeEnabled
    -0.56
    dojo
    -0.55
    XmlRootElement
    -0.52
     borsa
    -0.52
     scolas
    -0.51
     osmosis
    -0.50
     strconv
    -0.49
    Pragma
    -0.49
     sternum
    -0.49
     hjem
    -0.48
    POSITIVE LOGITS
     type
    2.02
     Type
    1.96
     TYPE
    1.83
    type
    1.73
     types
    1.63
    Type
    1.52
    TYPE
    1.50
     tipo
    1.45
     Types
    1.37
    types
    1.34
    Activations Density 0.235%

    No Known Activations