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. 1-GEMMASCOPE-RES-16K
    6. 13391
    Prev
    Next
    INDEX
    Explanations

    terms related to absorption, especially in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    k
    -0.48
    .
    -0.46
    ਘ
    -0.45
    功
    -0.44
     intr
    -0.44
     (
    -0.43
    *
    -0.43
    ^
    -0.43
    y
    -0.42
    5
    -0.42
    POSITIVE LOGITS
     Majefty
    1.36
    )");
    
    1.25
     Jefus
    1.22
     Efq
    1.20
     Shakspeare
    1.12
     Houſe
    1.12
    Personendaten
    1.11
     itſelf
    1.09
     Chriftian
    1.08
     Monfieur
    1.07
    Activations Density 0.089%

    No Known Activations