© 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. 5-GEMMASCOPE-RES-16K
    11. 3202
    Prev
    Next
    INDEX
    Explanations

    repeated phrases emphasizing consistency and continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muffins
    -0.90
     parís
    -0.87
     Noire
    -0.77
     bombe
    -0.77
    er
    -0.77
     âgées
    -0.76
    Niels
    -0.73
     Moderato
    -0.73
    脚注の使い方
    -0.72
     DisplayPort
    -0.71
    POSITIVE LOGITS
     always
    2.08
     Always
    1.97
    always
    1.91
     ALWAYS
    1.89
    Always
    1.88
    ALWAYS
    1.73
     alway
    1.41
     siempre
    1.40
    Siempre
    1.33
     Siempre
    1.33
    Activations Density 0.071%

    No Known Activations