© 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. 6780
    Prev
    Next
    INDEX
    Explanations

    concepts related to risk and safety in the context of environmental factors and potential hazards

    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
     MainAxisSize
    -0.92
    ########.
    -0.90
     Majefty
    -0.82
     Monfieur
    -0.80
    UserScript
    -0.79
     الدولى
    -0.78
     myſelf
    -0.78
    sizeCache
    -0.76
     AssemblyCulture
    -0.76
     WaitForSeconds
    -0.75
    POSITIVE LOGITS
    ,
    0.49
    使其
    0.48
    <eos>
    0.46
    setPassword
    0.45
     lemn
    0.43
     *
    0.40
    itinéraire
    0.40
    <<<<<<<
    0.40
     (
    0.39
     sinon
    0.39
    Activations Density 1.351%

    No Known Activations