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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 3460
    Prev
    Next
    INDEX
    Explanations

    terms related to defense and loyalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.66
    TintMode
    -0.59
     TAMBIÉN
    -0.59
     إل
    -0.56
    igshid
    -0.55
    heiser
    -0.52
     hoạch
    -0.52
    inaire
    -0.51
     AspNetCore
    -0.51
    audiovisuel
    -0.50
    POSITIVE LOGITS
     Defend
    1.07
     defend
    1.03
     defends
    0.98
     defended
    0.95
     defending
    0.93
     défendre
    0.82
     défend
    0.79
     DEFEND
    0.74
     indisponible
    0.72
     avenge
    0.72
    Activations Density 0.289%

    No Known Activations