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. 616
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "with" in various contexts

    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
    DebuggerNonUser
    -0.62
     dahlia
    -0.62
     SDR
    -0.60
     Ester
    -0.60
    Ester
    -0.59
     Untold
    -0.59
    tikzpicture
    -0.59
    itemBuilder
    -0.58
    tabular
    -0.58
    ূ
    -0.58
    POSITIVE LOGITS
     с
    1.41
     arşivlendi
    0.92
     със
    0.92
     со
    0.89
     С
    0.88
     з
    0.87
    WITH
    0.83
    С
    0.83
     עם
    0.82
    с
    0.82
    Activations Density 0.048%

    No Known Activations