© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 603
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific events and their details in a narrative context

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

    "one," "two," or numbers

    np_acts-logits-general · gemini-2.0-flash

    one and two

    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
    rungsseite
    -0.48
     Tah
    -0.41
    phosa
    -0.40
     canst
    -0.39
     restTemplate
    -0.39
     pluri
    -0.38
     band
    -0.38
    ſelf
    -0.38
     lenker
    -0.38
     Band
    -0.38
    POSITIVE LOGITS
     egyik
    0.57
    ScopeManager
    0.54
     یکی
    0.53
     one
    0.52
     niektó
    0.51
     jednego
    0.51
     één
    0.51
     некоторы
    0.50
     manchen
    0.49
     particularmente
    0.48
    Activations Density 0.712%

    No Known Activations