Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4294
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and terms related to safety and operational guidance

    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
    createCanvas
    -0.55
     sequenced
    -0.52
    ientôt
    -0.51
     atardecer
    -0.51
    มาะ
    -0.51
    udesta
    -0.48
     przecież
    -0.47
    locene
    -0.47
     Precambrian
    -0.47
    ViewFeatures
    -0.46
    POSITIVE LOGITS
    Erreferentziak
    0.66
    不必
    0.60
    +#+#
    0.60
     can
    0.59
    不用
    0.59
    bitField
    0.58
     safely
    0.58
    就可以
    0.56
    "):
    
    0.56
     mogen
    0.55
    Activations Density 0.352%

    No Known Activations