© 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. 5849
    Prev
    Next
    INDEX
    Explanations

    instructions for actions related to user interface navigation and management

    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
    tagHelperRunner
    -0.66
    SharedDtor
    -0.62
    出版年
    -0.56
    uxxxx
    -0.51
     humains
    -0.50
    
    -0.50
     noDo
    -0.49
     userSchema
    -0.48
    culoskeletal
    -0.47
    forts
    -0.47
    POSITIVE LOGITS
     instantly
    0.68
     szóci
    0.62
     instant
    0.59
     Instantly
    0.59
     instantaneously
    0.58
    OGND
    0.57
     automatically
    0.57
    tonode
    0.56
     automatiquement
    0.56
    icrous
    0.55
    Activations Density 0.390%

    No Known Activations