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. 16-GEMMASCOPE-RES-16K
    6. 1396
    Prev
    Next
    INDEX
    Explanations

    references to personal ownership or experiences, often indicated by the word "my" or possessive phrases

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

    Follows "My" and signals a personal expression (opinion, feeling, etc.)

    np_acts-logits-general · gemini-2.0-flash

    My followed by personal pronouns or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsonwebtoken
    -0.69
    ="/">
    -0.54
     AssemblyTitle
    -0.53
    ﷺ
    -0.53
    ImageContext
    -0.51
     בארץ
    -0.50
     aguda
    -0.49
    ännande
    -0.48
     springfox
    -0.48
    }$​
    -0.48
    POSITIVE LOGITS
     apologies
    0.69
    
    0.67
     guess
    0.66
     dear
    0.64
    fjspx
    0.62
    guess
    0.55
     favorite
    0.55
    laps
    0.54
     Goodness
    0.54
     goodness
    0.53
    Activations Density 0.126%

    No Known Activations