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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10447
    Prev
    Next
    INDEX
    Explanations

    phrases related to internet usage and online access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.58
    __(/*!
    -0.47
    SharedDtor
    -0.44
    Geplaatst
    -0.44
    fromCharCode
    -0.43
    Boxscore
    -0.41
    createClass
    -0.41
    segno
    -0.41
    แข
    -0.39
    Traceback
    -0.39
    POSITIVE LOGITS
     internet
    2.58
     Internet
    2.55
    Internet
    2.28
    internet
    2.27
     INTERNET
    2.06
    INTERNET
    1.83
    インターネット
    1.74
    互联网
    1.70
     internetu
    1.64
     интернет
    1.48
    Activations Density 0.308%

    No Known Activations