© 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. 4498
    Prev
    Next
    INDEX
    Explanations

    pronouns related to subjectivity and identity

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

    whether it be, alternative conditions

    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
     pleaſure
    -0.80
     purpoſe
    -0.75
     juſ
    -0.75
     faſt
    -0.74
     يتيمه
    -0.72
     للمعارف
    -0.71
     Inſ
    -0.69
     ſta
    -0.68
     ſte
    -0.66
     Reſ
    -0.65
    POSITIVE LOGITS
    不管是
    0.63
    无论是
    0.60
     whether
    0.55
     seja
    0.51
     either
    0.49
     Whether
    0.48
    Whether
    0.48
     be
    0.48
    posedge
    0.47
     سواء
    0.47
    Activations Density 0.007%

    No Known Activations