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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4500
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or criticisms relating to various contexts

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

    Text after a hyphen

    np_acts-logits-general · gemini-2.0-flash

    compound word components

    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
    -
    -0.96
    BorderFactory
    -0.53
    UnknownFieldSet
    -0.50
     Auvergne
    -0.49
     Monfieur
    -0.49
    ConverterFactory
    -0.48
    closePath
    -0.48
    jnych
    -0.47
     Myron
    -0.47
     cigars
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.65
     viewDidLoad
    0.61
     numberOfRows
    0.58
    帖最后由
    0.57
    thâu
    0.57
    ThroughAttribute
    0.56
     мѣ
    0.55
    SourceChecksum
    0.55
     الدولى
    0.54
     podjela
    0.53
    Activations Density 0.352%

    No Known Activations