© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5082
    Prev
    Next
    INDEX
    Explanations

    phrases that establish relationships or comparisons regarding various subjects

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

    "As far as," "with respect to," or "in terms of"

    np_acts-logits-general · gemini-2.0-flash

    when it comes to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
    Gesellschaft
    -0.28
     Gesellschaft
    -0.25
     hữu
    -0.23
     shy
    -0.23
     piloto
    -0.23
    ดย
    -0.22
     fol
    -0.22
    الإ
    -0.22
     succeeded
    -0.22
    设计师
    -0.21
    POSITIVE LOGITS
     autorytatywna
    0.93
    Concerning
    0.92
     regarding
    0.90
    regarding
    0.90
    Regarding
    0.88
     Concerning
    0.88
     betreft
    0.88
     bezüglich
    0.87
     riguarda
    0.86
     dotyczące
    0.86
    Activations Density 0.264%

    No Known Activations