© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14537
    Prev
    Next
    INDEX
    Explanations

    the start of a new section or paragraph in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idian
    -0.46
     ennemis
    -0.44
     (
    -0.44
    AHN
    -0.43
    depuis
    -0.42
     friendly
    -0.42
     (=
    -0.42
     [(
    -0.41
    arde
    -0.40
     absolutely
    -0.40
    POSITIVE LOGITS
    <bos>
    3.39
     Paglinawan
    1.47
     Савезне
    1.31
    Билгалдахарш
    1.30
    tagHelperRunner
    1.26
    DockStyle
    1.25
    Personendaten
    1.25
    IUrlHelper
    1.25
     disambiguazione
    1.22
    '
    1.14
    Activations Density 0.047%

    No Known Activations