© 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. 23-GEMMASCOPE-RES-16K
    6. 8613
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurements and experimental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppCompatTheme
    -0.71
     Anſ
    -0.66
     leaſt
    -0.65
    下载附件
    -0.65
    dymyr
    -0.65
     ſtate
    -0.64
    <?>>
    -0.64
     itſelf
    -0.64
     FormBuilder
    -0.61
    oodoo
    -0.61
    POSITIVE LOGITS
     per
    3.93
    per
    2.87
    Per
    2.77
     Per
    2.71
     PER
    2.33
    PER
    2.05
    PerPage
    1.21
     perse
    1.16
    perin
    1.16
    每
    1.15
    Activations Density 0.988%

    No Known Activations