© 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. 25-GEMMASCOPE-RES-16K
    11. 87
    Prev
    Next
    INDEX
    Explanations

    words related to aggressive behaviors and their influences, particularly in children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.81
     المعيارى
    -0.75
    expandindo
    -0.70
    nskap
    -0.59
    ReusableCell
    -0.58
     AssemblyCompany
    -0.57
    EReference
    -0.56
     ligiloj
    -0.55
     ExecuteAsync
    -0.55
    kinin
    -0.53
    POSITIVE LOGITS
     behavior
    2.37
     behaviour
    2.21
     behaviors
    2.04
    behavior
    1.96
     Behavior
    1.92
     behaviours
    1.88
     Behaviour
    1.74
    Behavior
    1.71
     BEHAVIOR
    1.71
     comportement
    1.70
    Activations Density 0.805%

    No Known Activations