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. 3689
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to margin and padding

    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
    ########.
    -0.81
     Chwiliwch
    -0.55
    ĩa
    -0.54
     Sult
    -0.53
    émoc
    -0.53
    <?,
    -0.52
     continúas
    -0.52
     Anſ
    -0.52
     completeness
    -0.51
     препратки
    -0.51
    POSITIVE LOGITS
     margin
    3.19
    margin
    3.15
     Margin
    2.83
    Margin
    2.65
     margins
    2.61
    MARGIN
    2.15
    margins
    2.01
    Margins
    1.81
     marginal
    1.72
     Marginal
    1.68
    Activations Density 0.046%

    No Known Activations