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. 18-GEMMASCOPE-RES-16K
    6. 3173
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to various industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Specific sectors or industries

    np_acts-logits-general · gemini-2.0-flash

    industries and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.77
    IsContent
    -0.69
     klok
    -0.69
    DockStyle
    -0.67
     dezelve
    -0.61
    tagHelperRunner
    -0.59
    ]--;
    -0.58
     auroit
    -0.57
    AddTagHelper
    -0.57
     Landwirtschaft
    -0.57
    POSITIVE LOGITS
     industry
    0.82
     sector
    0.69
    industry
    0.58
    örté
    0.57
     GetEnumerator
    0.56
     professionals
    0.53
    界
    0.53
     profession
    0.52
     community
    0.52
     companies
    0.52
    Activations Density 0.585%

    No Known Activations