© 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. 1761
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements and official statements

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

    followed by "announced" or a derivative

    np_acts-logits-general · gemini-2.0-flash

    reporting and announcing events

    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
     незавершена
    -0.84
     HasFactory
    -0.70
    Personendaten
    -0.61
     CWE
    -0.59
     convertView
    -0.58
     pylint
    -0.57
     auffi
    -0.56
     GenerationType
    -0.56
    DeleteBehavior
    -0.54
    RetentionPolicy
    -0.53
    POSITIVE LOGITS
     announcement
    2.69
     announced
    2.42
     announce
    2.39
     announcing
    2.36
     announcements
    2.35
     Announcement
    2.19
     ANNOUNC
    2.16
     announces
    2.14
    announcement
    2.05
    Announcement
    2.03
    Activations Density 0.236%

    No Known Activations