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. 16316
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags and their attributes in the document

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

    "string" data type

    np_acts-logits-general · gemini-2.0-flash

    property string

    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
    Palmarès
    -0.55
     متعلقه
    -0.55
    estacks
    -0.52
     незавершена
    -0.50
    thâu
    -0.49
     урна
    -0.48
    دانشنامهٔ
    -0.48
     <<<<<<<<<<<<<<
    -0.46
     factor
    -0.46
     للمعارف
    -0.46
    POSITIVE LOGITS
     string
    2.47
    string
    2.44
     strings
    1.05
     strung
    0.90
    STRING
    0.87
    tring
    0.86
     STRING
    0.83
    strings
    0.75
     sting
    0.74
    字符串
    0.74
    Activations Density 0.101%

    No Known Activations