© 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. 31-GEMMASCOPE-RES-16K
    11. 8215
    Prev
    Next
    INDEX
    Explanations

    mentions of announcements or updates related to organizations or companies

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

    first-person singular pronouns and past tense verbs describing personal actions or experiences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     later
    -0.98
     später
    -0.86
     pozdě
    -0.84
     recent
    -0.83
     później
    -0.83
     obecnie
    -0.81
     aujourd
    -0.81
     senare
    -0.81
     späteren
    -0.81
     today
    -0.79
    POSITIVE LOGITS
     officially
    0.59
     announced
    0.57
    IonicModule
    0.56
    again
    0.55
     suddenly
    0.55
     unexpectedly
    0.55
     again
    0.54
    ManagedBean
    0.54
     formally
    0.54
    UrlResolution
    0.54
    Activations Density 0.574%

    No Known Activations