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. 14-GEMMASCOPE-RES-16K
    6. 10457
    Prev
    Next
    INDEX
    Explanations

    elements related to identity and transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")
    -0.60
     trattano
    -0.55
     Rima
    -0.53
     Wund
    -0.52
     simpl
    -0.52
     "));
    -0.52
    bias
    -0.52
    zeciw
    -0.51
     newOwner
    -0.51
    Bias
    -0.51
    POSITIVE LOGITS
    
    0.68
     imperson
    0.64
     disguise
    0.64
     cloned
    0.63
     imposter
    0.61
     identity
    0.57
     impostor
    0.56
     disgu
    0.55
    cloned
    0.55
     masquer
    0.54
    Activations Density 0.363%

    No Known Activations