© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 3952
    Prev
    Next
    INDEX
    Explanations

    statements regarding problems and limitations in methodologies or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.57
     albero
    -0.56
     paraître
    -0.54
     particulières
    -0.54
     préféré
    -0.53
     Syrie
    -0.53
     destacado
    -0.53
     ederim
    -0.51
    pyx
    -0.51
     nî
    -0.51
    POSITIVE LOGITS
    EDEFAULT
    0.83
     outdated
    0.70
    solete
    0.70
    SpringBootTest
    0.68
     unsuitable
    0.66
    ChildScrollView
    0.65
    AnimationsModule
    0.65
     inadequate
    0.64
    basicConfig
    0.64
    rateur
    0.64
    Activations Density 0.422%

    No Known Activations