Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 509
    Prev
    Next
    INDEX
    Explanations

    collective pronouns and expressions of inclusivity

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

    uses of the first-person plural point of view (inclusive group references like we/us/our).

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ization
    -0.50
    اً
    -0.45
    poz
    -0.45
    ment
    -0.44
    oid
    -0.44
    ly
    -0.43
    ction
    -0.43
     yourself
    -0.43
    ggior
    -0.42
     entry
    -0.42
    POSITIVE LOGITS
    We
    0.99
     we
    0.91
     We
    0.88
     jsme
    0.77
    we
    0.77
     เรา
    0.77
     meille
    0.77
    WE
    0.72
     CreateTagHelper
    0.71
    Мы
    0.70
    Activations Density 0.335%

    No Known Activations