© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7960
    Prev
    Next
    INDEX
    Explanations

    terms related to audio and broadcasting technology

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

    Audio equipment and related terminology

    np_acts-logits-general · gemini-2.0-flash

    audio mixers and microphones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doPost
    -0.65
     magasiner
    -0.60
    abank
    -0.57
    EndTag
    -0.56
    
    -0.53
    siąż
    -0.53
    __':
    -0.53
    __':
    -0.51
    Makefile
    -0.51
     argc
    -0.50
    POSITIVE LOGITS
     mic
    0.74
     condenser
    0.71
     Mackie
    0.70
     cardio
    0.65
     mixer
    0.65
     Dante
    0.64
     mics
    0.64
     mixers
    0.61
     microphone
    0.61
     Neumann
    0.59
    Activations Density 0.144%

    No Known Activations