© 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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4417
    Prev
    Next
    INDEX
    Explanations

    text that contains references to official websites and additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.93
     незавершена
    -0.92
    AddTagHelper
    -0.89
    tagHelperRunner
    -0.89
    OGND
    -0.85
    AndEndTag
    -0.78
    WriteTagHelper
    -0.76
    كويكب
    -0.74
    PyExc
    -0.73
    UnusedPrivate
    -0.72
    POSITIVE LOGITS
     website
    0.57
    公式サイト
    0.46
    Website
    0.45
    の情報
    0.45
    visit
    0.45
    https
    0.44
     online
    0.43
    Visit
    0.43
     details
    0.42
     Website
    0.42
    Activations Density 0.114%

    No Known Activations