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. 15-GEMMASCOPE-RES-16K
    6. 12964
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ─
    -0.80
     –,
    -0.77
    Portale
    -0.73
    ]),
    
    -0.73
     itſelf
    -0.72
    ’”
    -0.72
     ſind
    -0.71
    .³
    -0.71
     '\\;'
    -0.70
     ་་
    -0.69
    POSITIVE LOGITS
     I
    0.93
     
    0.74
     guys
    0.64
     ppl
    0.63
    I
    0.63
     my
    0.61
     ihop
    0.61
    .....
    0.61
     something
    0.60
     yg
    0.60
    Activations Density 0.193%

    No Known Activations