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. 23-GEMMASCOPE-RES-16K
    6. 12391
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional struggle and feelings of inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onViewCreated
    -0.61
    WebControls
    -0.61
    Composable
    -0.59
    WebServlet
    -0.57
    GOTREF
    -0.57
    RegistryLite
    -0.56
     mümkün
    -0.53
    ligently
    -0.52
     مواليد
    -0.52
     Italijanski
    -0.52
    POSITIVE LOGITS
     discriminated
    0.79
     marginalized
    0.77
     laughed
    0.73
     stigmati
    0.73
     ostra
    0.73
     excluded
    0.72
     left
    0.65
     margin
    0.65
     outcast
    0.64
     disadvantaged
    0.63
    Activations Density 0.318%

    No Known Activations