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. 20-GEMMASCOPE-RES-16K
    6. 15657
    Prev
    Next
    INDEX
    Explanations

    prepositions or similar connecting words indicating location or position

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

    "auf", "na", or similar non-English word

    np_acts-logits-general · gemini-2.0-flash

    prepositions in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}")
    -0.67
    MemoryWarning
    -0.65
    AndEndTag
    -0.65
    .")
    
    -0.61
    )])
    -0.61
     Público
    -0.60
    utivos
    -0.58
     NSCoder
    -0.58
    "})
    -0.57
     myſelf
    -0.57
    POSITIVE LOGITS
    SequentialGroup
    0.73
     linkovi
    0.56
     utafitiHapana
    0.53
     harapan
    0.52
     occasion
    0.51
    RegressionTest
    0.51
     basis
    0.51
    jsxFileName
    0.49
    Παραπομπές
    0.48
    verwijspagina
    0.47
    Activations Density 0.017%

    No Known Activations