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. 4501
    Prev
    Next
    INDEX
    Explanations

    references to local government structures and community integration

    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
     zwar
    -0.54
     such
    -0.49
     SUCH
    -0.49
    tako
    -0.45
     eg
    -0.43
     galite
    -0.43
    laß
    -0.42
     into
    -0.42
     Such
    -0.42
     descarga
    -0.42
    POSITIVE LOGITS
    Cyfeiriadau
    0.92
    StoreMessageInfo
    0.91
     Shakspeare
    0.89
     >=",
    0.87
     Efq
    0.84
     Majefty
    0.83
    BeginContext
    0.82
    /**
    0.82
     Lordships
    0.81
    ſelves
    0.80
    Activations Density 0.444%

    No Known Activations