© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1193
    Prev
    Next
    INDEX
    Explanations

    phrases that address the reader directly and indicate personal agency or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyTitle
    -0.92
    SourceChecksum
    -0.92
    ########.
    -0.79
    tagHelperRunner
    -0.77
    principalTable
    -0.76
    rxjs
    -0.75
     AspNetCore
    -0.74
     cherchés
    -0.72
    Personensuche
    -0.71
    AddTagHelper
    -0.71
    POSITIVE LOGITS
     yourself
    1.90
     your
    1.51
    yourself
    1.43
    your
    1.35
     Yourself
    1.26
     YOURSELF
    1.23
    Yourself
    1.21
    Your
    1.18
     yourselves
    1.15
     Your
    1.12
    Activations Density 1.321%

    No Known Activations