Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15692
    Prev
    Next
    INDEX
    Explanations

    references to the word "come" and its variations, indicating a focus on invitations or actions to join

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.63
    protoimpl
    -0.57
     sebaliknya
    -0.57
    findpost
    -0.54
    CloseOperation
    -0.54
    anzug
    -0.52
    ekš
    -0.49
    Transcript
    -0.48
     khuẩn
    -0.48
    Locality
    -0.48
    POSITIVE LOGITS
     defaultstate
    0.64
    Come
    0.54
     blow
    0.51
     JB
    0.51
    存于互联网档案馆
    0.51
     fisherman
    0.50
    jay
    0.50
    .~(\
    0.50
    omé
    0.50
     springfox
    0.49
    Activations Density 0.062%

    No Known Activations