© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4484
    Prev
    Next
    INDEX
    Explanations

    expressions of respect and acknowledgment of individual choices

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

    Follows "pure", "likely", or ","

    np_acts-logits-general · gemini-2.0-flash

    intention and sincerity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.45
    存于互联网档案馆
    -0.42
     houſe
    -0.40
     anſ
    -0.39
     Reward
    -0.39
     wireType
    -0.38
     Mémoires
    -0.37
    awtextra
    -0.37
     Anſ
    -0.36
    bootstrapcdn
    -0.35
    POSITIVE LOGITS
     intentions
    1.13
     sincere
    1.01
     intention
    0.96
     sincerely
    0.93
     intent
    0.89
     genuinely
    0.88
     intenciones
    0.84
     genuine
    0.83
     Inten
    0.81
     Intent
    0.81
    Activations Density 0.366%

    No Known Activations