Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 796
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks and narrative pauses

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

    Word immediately after an ellipsis

    np_acts-logits-general · gemini-2.0-flash

    well, mostly

    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
     therefore
    -0.38
     pilas
    -0.37
     arşivlendi
    -0.37
    PostInfinity
    -0.37
     hijas
    -0.36
    intéress
    -0.36
     Masyarakat
    -0.35
     corrientes
    -0.35
    pertory
    -0.35
     richt
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.52
    WebServlet
    0.47
    addPreferredGap
    0.46
    bufio
    0.44
     nakalista
    0.44
    SpringBootTest
    0.43
    €¦
    0.43
    styleType
    0.43
    帖最后由
    0.43
     PropertyChanged
    0.42
    Activations Density 0.151%

    No Known Activations