© 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. 12-GEMMASCOPE-RES-16K
    6. 10646
    Prev
    Next
    INDEX
    Explanations

    references to locations and organizations, particularly in Ireland and references to medical and scientific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aiheesta
    -0.73
    HostException
    -0.71
     continúas
    -0.53
    ỳnh
    -0.51
    jahtera
    -0.49
    -------
    
    -0.48
    rsquo
    -0.47
    ViewById
    -0.47
    وردار
    -0.47
    pacho
    -0.46
    POSITIVE LOGITS
     &
    1.33
    &
    1.06
    &
    1.02
     \&
    1.02
     $\&$
    0.90
    \&
    0.86
     itſelf
    0.83
    And
    0.77
     &,
    0.76
     &.
    0.76
    Activations Density 1.212%

    No Known Activations