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. 12-GEMMASCOPE-RES-16K
    6. 900
    Prev
    Next
    INDEX
    Explanations

    instances of standalone "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.89
     архивлан
    -0.76
    verwijspagina
    -0.70
    fromnode
    -0.70
    windowFixed
    -0.69
    oa̍t
    -0.69
    nocache
    -0.68
    URLException
    -0.66
    verifyException
    -0.65
    AddTagHelper
    -0.59
    POSITIVE LOGITS
     artistico
    0.55
    dată
    0.53
    __(/*!
    0.51
     dépasse
    0.51
    gnose
    0.50
    upakan
    0.49
     iconFacebook
    0.49
    projekt
    0.48
     animé
    0.47
     enfrentan
    0.47
    Activations Density 0.009%

    No Known Activations