© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6498
    Prev
    Next
    INDEX
    Explanations

    references to speeches and public speaking events

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

    before "speech" or "argument"

    np_acts-logits-general · gemini-2.0-flash

    giving a speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    సు
    -0.65
     resourceCulture
    -0.56
    TargetException
    -0.55
     autorytatywna
    -0.54
     Screenshots
    -0.54
    ետ
    -0.53
     unittest
    -0.53
     CreateTagHelper
    -0.53
    PageRoute
    -0.51
    MigrationBuilder
    -0.51
    POSITIVE LOGITS
     speech
    2.01
     speeches
    1.77
    speech
    1.63
     Speech
    1.61
     speaking
    1.60
     speakers
    1.48
     speaker
    1.48
     speak
    1.44
    Speech
    1.44
     SPEECH
    1.43
    Activations Density 0.312%

    No Known Activations