© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107409
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences related to expressing understanding, ability, and existence

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

    self-reference and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -0.32
     murky
    -0.27
    этому
    -0.27
    <eos>
    -0.26
     my
    -0.26
    ℗
    -0.26
    によっては
    -0.25
     spot
    -0.24
     توانید
    -0.24
     di
    -0.23
    POSITIVE LOGITS
    ſelves
    0.87
     Anſ
    0.80
     anſ
    0.78
     leaſt
    0.78
     juſ
    0.76
    ſelf
    0.75
     imagui
    0.74
    <unused73>
    0.73
    <unused20>
    0.73
    <unused93>
    0.73
    Activations Density 0.024%

    No Known Activations