© 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. 16-GEMMASCOPE-RES-16K
    11. 14530
    Prev
    Next
    INDEX
    Explanations

    attributes related to appealing qualities and suitability of entities, particularly in contexts involving venues or candidates

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

    Makes [pronoun] [adjective]

    np_acts-logits-general · gemini-2.0-flash

    qualifies or makes suitable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.70
    IBOutlet
    -0.67
    NameInMap
    -0.65
     betweenstory
    -0.64
    :✨
    -0.64
     IBOutlet
    -0.63
    SharedCtor
    -0.62
    GeneratedCode
    -0.61
    due
    -0.60
    protoimpl
    -0.59
    POSITIVE LOGITS
     uniquely
    0.63
     trở
    0.62
     layak
    0.60
    akterysty
    0.59
     unique
    0.58
     easily
    0.56
     Unique
    0.55
     significantly
    0.53
     qualifies
    0.53
     hini
    0.53
    Activations Density 0.245%

    No Known Activations