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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4116
    Prev
    Next
    INDEX
    Explanations

    statements regarding the presence or absence of evidence and opinions in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences asserting existence ("there is ...")

    np_acts-logits-general · gemini-2.0-flash

    there is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HideFlags
    -0.48
     shi
    -0.47
     coron
    -0.46
    ↦
    -0.45
     balls
    -0.44
     jam
    -0.44
     dur
    -0.44
     lauter
    -0.44
    脚注の使い方
    -0.44
     Chand
    -0.44
    POSITIVE LOGITS
     evidence
    0.52
    证据
    0.45
    evidence
    0.42
     ragioni
    0.42
     esiste
    0.39
     reason
    0.39
     alcuna
    0.39
     tendenza
    0.39
     istnie
    0.38
     asimismo
    0.38
    Activations Density 0.488%

    No Known Activations