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. 17-GEMMASCOPE-RES-16K
    6. 1124
    Prev
    Next
    INDEX
    Explanations

    mentions of UN reports or globalization efforts related to human rights and refugee assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.69
    UpInside
    -0.51
     ride
    -0.48
     muualla
    -0.46
    gä
    -0.46
     Kimmel
    -0.45
     manejo
    -0.45
    ardless
    -0.44
     Vick
    -0.43
    strategia
    -0.42
    POSITIVE LOGITS
    Portail
    0.81
     chi̍t
    0.74
     Efq
    0.73
    UnusedPrivate
    0.68
    enderror
    0.66
    Personendaten
    0.66
     propOrder
    0.65
     smtplib
    0.64
     contextLoads
    0.64
     nakalista
    0.64
    Activations Density 0.088%

    No Known Activations