© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2693
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic evaluations and assessments by a commission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     folks
    -0.68
     isn
    -0.64
     horrible
    -0.57
     aren
    -0.56
     things
    -0.55
    Percent
    -0.49
     quitar
    -0.49
     someplace
    -0.49
     doesn
    -0.49
     insanely
    -0.48
    POSITIVE LOGITS
     envisaged
    1.15
     favourably
    0.96
     Reverso
    0.95
     colourless
    0.94
     envisage
    0.92
     authorisation
    0.91
     characterised
    0.90
     realisation
    0.88
     mobilisation
    0.88
    personalised
    0.87
    Activations Density 0.523%

    No Known Activations