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. 18-GEMMASCOPE-RES-16K
    6. 9960
    Prev
    Next
    INDEX
    Explanations

    the past tense form of the verb "to be."

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

    Followed by a past participle or adjective

    np_acts-logits-general · gemini-2.0-flash

    past origins or states

    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
    WithMany
    -0.56
    Parms
    -0.53
    +#+#
    -0.52
    parseFrom
    -0.51
     Ouverture
    -0.45
    soort
    -0.45
     curent
    -0.45
     Garrick
    -0.44
     curr
    -0.43
    üş
    -0.43
    POSITIVE LOGITS
     autrefois
    1.27
     vroeger
    1.05
     previously
    1.03
     formerly
    0.99
    previously
    0.97
     originally
    0.94
     recently
    0.91
     originalmente
    0.90
     ursprünglich
    0.87
    Previously
    0.86
    Activations Density 0.392%

    No Known Activations