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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3724
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters within a text

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

    Unicode characters

    np_acts-logits-general · gemini-2.0-flash

    unicode sequences and escape characters

    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
     himo
    -1.06
    Diwedd
    -1.00
    DockStyle
    -0.97
    Vidite
    -0.93
    CodedInputStream
    -0.92
    ImageContext
    -0.90
    NameInMap
    -0.90
    ConstraintMaker
    -0.86
     Administrativna
    -0.86
    клопе
    -0.85
    POSITIVE LOGITS
     
    0.51
     rowspan
    0.50
      (
    0.50
    ".$_
    0.50
    ("")]
    0.49
     Horv
    0.49
    DaoImpl
    0.48
    ">'.$
    0.47
    saver
    0.47
    EQU
    0.46
    Activations Density 0.174%

    No Known Activations