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. 14-GEMMASCOPE-RES-16K
    6. 10592
    Prev
    Next
    INDEX
    Explanations

    technical terms and library imports related to Java programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.27
    ReusableCell
    -1.16
    +#+#
    -1.09
    PreferredItem
    -1.02
    ]")]
    -1.02
     مشين
    -0.99
    AnchorStyles
    -0.98
    URLException
    -0.97
     unknownFields
    -0.96
     IBOutlet
    -0.96
    POSITIVE LOGITS
    <sup>
    0.45
     circo
    0.41
     monte
    0.41
    asso
    0.41
     ImGui
    0.39
     présent
    0.39
     Gehirn
    0.39
     grosso
    0.39
    middelen
    0.38
     وصلة
    0.38
    Activations Density 0.439%

    No Known Activations