Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 5107
    Prev
    Next
    INDEX
    Explanations

    terms related to business and medical terminology, particularly focusing on bladder-related functions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Winaray
    -0.81
    ArgsConstructor
    -0.71
    yntaxException
    -0.67
    migrationBuilder
    -0.66
    AddTagHelper
    -0.65
    queryInterface
    -0.64
     gql
    -0.61
    actionMode
    -0.60
    DockStyle
    -0.60
    nościo
    -0.60
    POSITIVE LOGITS
     BPD
    1.01
     BEM
    1.00
     bArr
    0.95
     BPS
    0.94
     BH
    0.90
     BCS
    0.89
     bps
    0.89
     getB
    0.89
     Bhat
    0.88
     Bh
    0.86
    Activations Density 3.310%

    No Known Activations