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. 22-GEMMASCOPE-RES-16K
    6. 13818
    Prev
    Next
    INDEX
    Explanations

    elements related to SMS verification and confirmation processes

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

    Non-English words or phrases

    np_acts-logits-general · gemini-2.0-flash

    mathematical elements, foreign words

    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
     Monfieur
    -0.86
     Reſ
    -0.82
    IntoConstraints
    -0.82
     Jefus
    -0.79
     ſtate
    -0.76
     Diſ
    -0.74
     pleaſure
    -0.73
     Conſ
    -0.73
     iſt
    -0.72
     purpoſe
    -0.72
    POSITIVE LOGITS
     kvinder
    0.51
     marins
    0.49
     Best
    0.47
     melhor
    0.47
     nationaux
    0.46
     européennes
    0.46
     вы
    0.45
     meilleurs
    0.44
     børn
    0.44
    ngths
    0.43
    Activations Density 0.045%

    No Known Activations