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. 19-GEMMASCOPE-RES-16K
    6. 2193
    Prev
    Next
    INDEX
    Explanations

    specific labels or identifiers related to figures and sections in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.06
    IUrlHelper
    -0.74
    thenReturn
    -0.69
     BoxDecoration
    -0.62
    ValueStyle
    -0.61
    estris
    -0.57
    ViewFeatures
    -0.57
     iconFacebook
    -0.57
     EconPapers
    -0.56
    merksam
    -0.55
    POSITIVE LOGITS
     forti
    0.47
    yes
    0.44
    pcm
    0.44
     Dac
    0.44
    SPATH
    0.43
    częściej
    0.43
    μφωνα
    0.43
    チュ
    0.42
     doPost
    0.42
     Lijst
    0.42
    Activations Density 0.595%

    No Known Activations