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. 2-GEMMASCOPE-RES-16K
    6. 6804
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.09
     houſe
    -1.08
     poffe
    -1.05
     ſtate
    -1.04
     pleaſure
    -1.02
     faſt
    -0.99
     ſtill
    -0.95
     ſta
    -0.94
     Monfieur
    -0.93
     ſte
    -0.91
    POSITIVE LOGITS
    WebVitals
    0.77
      
    0.58
    PrototypeOf
    0.56
    #!/
    0.56
    defineProperty
    0.55
    lateinit
    0.55
     ‘
    0.53
     of
    0.52
    ագրություններ
    0.51
     distinguer
    0.51
    Activations Density 0.205%

    No Known Activations