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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15386
    Prev
    Next
    INDEX
    Explanations

    terms related to verification and communication on social media platforms, particularly focusing on SMS and account confirmation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.69
     fashiola
    -0.68
    ulemon
    -0.68
    atrici
    -0.66
     decedent
    -0.66
    kemeja
    -0.66
    entibus
    -0.66
    majánló
    -0.65
    Elenco
    -0.64
     AssemblyCulture
    -0.63
    POSITIVE LOGITS
     inder
    0.31
     depositphotos
    0.30
     assurent
    0.27
    馃
    0.26
     "":
    0.26
     (...)
    0.26
     europa
    0.26
    Hozzáférés
    0.25
     fecond
    0.24
     گوش
    0.24
    Activations Density 0.092%

    No Known Activations