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. 4-GEMMASCOPE-RES-16K
    6. 535
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and related demonstrative pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oublié
    -0.66
    principalTable
    -0.64
    \{\\
    -0.64
    ClientRect
    -0.62
    клопе
    -0.59
     demain
    -0.59
    Tikang
    -0.58
     sinon
    -0.57
    Clik
    -0.56
     برانيه
    -0.56
    POSITIVE LOGITS
     This
    1.47
    This
    1.42
     These
    0.94
    These
    0.91
     وهذا
    0.88
     Diese
    0.74
    Cette
    0.74
    Esta
    0.74
     Esto
    0.74
     Detta
    0.74
    Activations Density 0.222%

    No Known Activations