© 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. 5264
    Prev
    Next
    INDEX
    Explanations

    references to creative projects and articles, particularly in the context of products, ideas, and various forms of media

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

    Followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    many entities

    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
    Datuak
    -0.69
     ujednoznacz
    -0.66
    Personendaten
    -0.65
    IntoConstraints
    -0.65
    InjectAttribute
    -0.63
     noDo
    -0.60
     queſta
    -0.59
     Numerade
    -0.59
    Vidite
    -0.58
     հղումներ
    -0.57
    POSITIVE LOGITS
     many
    0.54
     Many
    0.51
     MANY
    0.50
    Many
    0.50
    many
    0.49
     viele
    0.47
     nombreuses
    0.46
     different
    0.45
    MANY
    0.43
     nombreux
    0.43
    Activations Density 0.609%

    No Known Activations