© 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. 3-GEMMASCOPE-RES-16K
    11. 5920
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases involving the word "by."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.74
    EndInit
    -0.68
     *-
    -0.63
    EDEFAULT
    -0.61
    SerializedSize
    -0.60
    ngdoc
    -0.60
    ScopeManager
    -0.60
    ItemBackground
    -0.59
     HasFactory
    -0.59
    invokeLater
    -0.58
    POSITIVE LOGITS
    OGND
    0.71
    
    0.58
     everyone
    0.53
    lectic
    0.49
    řeb
    0.49
     الجمه
    0.47
     everybody
    0.46
     跳转至
    0.46
     لدى
    0.45
    raham
    0.45
    Activations Density 0.295%

    No Known Activations