© 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. 22-GEMMASCOPE-RES-16K
    11. 3654
    Prev
    Next
    INDEX
    Explanations

    discussions related to personal experiences and opinions about relationships

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

    preceding modal verbs

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.05
     whoſe
    -0.97
     Majefty
    -0.95
     NDEBUG
    -0.92
    —”
    -0.89
     uſ
    -0.89
     houſe
    -0.88
     ―――――
    -0.88
     Houſe
    -0.88
     ſeveral
    -0.87
    POSITIVE LOGITS
     dont
    1.02
     alot
    0.94
     didnt
    0.93
     loosing
    0.88
     betek
    0.87
     wasnt
    0.83
     doesnt
    0.83
     atleast
    0.81
     wont
    0.80
     realy
    0.80
    Activations Density 0.705%

    No Known Activations