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. 14699
    Prev
    Next
    INDEX
    Explanations

    terms related to dosage, concentration, or species specificity in a biological context

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

    dependence or dose of substance/process

    np_acts-logits-general · gemini-2.0-flash

    specific type and dependence

    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
    IContainer
    -0.65
    UrlResolution
    -0.58
    VisualStudio
    -0.54
     caminh
    -0.52
     demais
    -0.51
     azzurro
    -0.50
     Ogil
    -0.50
     urbanos
    -0.49
     connus
    -0.49
     aço
    -0.49
    POSITIVE LOGITS
     specific
    1.37
    specific
    1.22
     dependent
    1.20
    Specific
    1.13
     Specific
    1.10
    pecific
    1.09
    dependent
    1.03
    별
    1.01
     Dependent
    1.01
     SPECIFIC
    1.01
    Activations Density 0.859%

    No Known Activations