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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 14939
    Prev
    Next
    INDEX
    Explanations

    permissions and identifiers related to device state

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

    Code, methods, or settings

    np_acts-logits-general · gemini-2.0-flash

    permissions, startActivity, Audio, light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ême
    -0.49
     løpet
    -0.49
    หัว
    -0.45
    LogFactory
    -0.43
    كة
    -0.41
    üğ
    -0.41
    ANTLR
    -0.41
    판
    -0.41
    ktm
    -0.41
    cnc
    -0.40
    POSITIVE LOGITS
    Autoritní
    0.96
     autorytatywna
    0.87
    AndEndTag
    0.86
    ActivityCompat
    0.82
     فريبيس
    0.70
    PickerController
    0.65
    chymal
    0.64
     otomatig
    0.64
    रीदारी
    0.63
    +#+#
    0.63
    Activations Density 0.185%

    No Known Activations