© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 471
    Prev
    Next
    INDEX
    Explanations

    terms related to refutation and denial in arguments or statements

    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
    索
    -0.52
     specially
    -0.49
     especial
    -0.48
    Primitives
    -0.47
    VersionUID
    -0.45
     Specially
    -0.44
     demander
    -0.43
    త
    -0.43
     value
    -0.42
     Ca
    -0.41
    POSITIVE LOGITS
     refuted
    1.02
     refute
    0.97
     dispel
    0.96
     rebuttal
    0.93
     disprove
    0.84
    BeginInit
    0.83
    spesies
    0.75
    \{\\
    0.75
    IUrlHelper
    0.75
     retort
    0.72
    Activations Density 0.710%

    No Known Activations