© 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. 28-GEMMASCOPE-RES-16K
    11. 7424
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational roles and statements

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

    followed by "said" or "says"

    np_acts-logits-general · gemini-2.0-flash

    reporting speech or findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.41
     }}-
    -0.34
    ⟬
    -0.34
    MemoryWarning
    -0.34
     mig
    -0.33
    }/
    -0.33
    IntentFilter
    -0.33
    EndContext
    -0.33
    tagHelper
    -0.30
     kamp
    -0.30
    POSITIVE LOGITS
     said
    1.67
     says
    1.50
     mengatakan
    1.42
     stated
    1.25
    says
    1.24
    Says
    1.23
    said
    1.23
     remarked
    1.19
     saying
    1.18
     Says
    1.18
    Activations Density 1.180%

    No Known Activations