© 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. 18-GEMMASCOPE-RES-16K
    11. 9563
    Prev
    Next
    INDEX
    Explanations

    references to manipulative behaviors and the influence of media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding expressions of intent or desire

    np_acts-logits-general · gemini-2.0-flash

    publicity and attention seeking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sério
    -0.67
     nahilalakip
    -0.55
     verdadeira
    -0.53
    قيقي
    -0.52
     réellement
    -0.52
     alvor
    -0.51
     vraie
    -0.51
     autén
    -0.50
     verdadera
    -0.49
     verdaderos
    -0.49
    POSITIVE LOGITS
     convenient
    0.79
     Convenient
    0.76
     convenience
    0.72
    Convenient
    0.72
     expediency
    0.71
     CanadaChoose
    0.71
    convenient
    0.70
     appease
    0.69
    convenience
    0.69
     pleasing
    0.67
    Activations Density 0.538%

    No Known Activations