© 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. 863
    Prev
    Next
    INDEX
    Explanations

    words related to confirmation and verification in a technological context

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

    Beginning of Croatian words and some English words

    np_acts-logits-general · gemini-2.0-flash

    Croatian user interface elements

    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
     
    -0.52
     no
    -0.51
     ng
    -0.49
     base
    -0.46
     point
    -0.46
     set
    -0.45
     it
    -0.45
     ay
    -0.45
     f
    -0.45
    ,
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.95
     myſelf
    0.93
     незавершена
    0.92
     Efq
    0.92
    ConstraintMaker
    0.92
     Normdatei
    0.91
     noDo
    0.90
     pleaſure
    0.88
    GEBURTSDATUM
    0.88
    ſelves
    0.87
    Activations Density 0.050%

    No Known Activations