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. 25-GEMMASCOPE-RES-16K
    6. 3349
    Prev
    Next
    INDEX
    Explanations

    technical terms and indicators related to data analysis and representation in scientific contexts

    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
    FormState
    -0.52
     AssemblyTitle
    -0.50
    matchCondition
    -0.48
     sokak
    -0.47
     säll
    -0.47
    principalTable
    -0.47
     AspNetCore
    -0.46
    abord
    -0.44
     adil
    -0.43
     kadar
    -0.43
    POSITIVE LOGITS
     arrows
    1.17
     dashed
    1.17
     dotted
    1.04
    dashed
    1.03
     arrow
    1.03
    solid
    1.00
     shaded
    0.99
     solid
    0.96
     inset
    0.96
     Arrows
    0.95
    Activations Density 1.707%

    No Known Activations