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. 25-GEMMASCOPE-RES-16K
    6. 4267
    Prev
    Next
    INDEX
    Explanations

    references to Android and Apache libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heinemann
    -0.45
    mucha
    -0.43
    queryInterface
    -0.43
    literals
    -0.42
     Daun
    -0.41
    glClear
    -0.41
     –,
    -0.41
    deren
    -0.41
     Vedi
    -0.41
     Nadel
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.76
     المعيارى
    0.65
     فريبيس
    0.63
    MemoryWarning
    0.61
    GEBURTSDATUM
    0.59
    MethodManager
    0.58
     Normdatei
    0.57
    __(/*!
    0.57
    fjspx
    0.57
    DebuggerNonUser
    0.57
    Activations Density 0.095%

    No Known Activations