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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2922
    Prev
    Next
    INDEX
    Explanations

    text related to various types of difficulties or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.50
     Italijani
    -0.50
     OMITBAD
    -0.49
    ScopeManager
    -0.48
    MLLoader
    -0.47
     CreateTagHelper
    -0.45
     propOrder
    -0.45
    WriteTagHelper
    -0.45
     تضيفلها
    -0.44
    piram
    -0.44
    POSITIVE LOGITS
     troubles
    2.17
     problems
    2.08
     problem
    2.03
     trouble
    1.98
    problem
    1.96
    problems
    1.94
     Problems
    1.91
     Problem
    1.90
    Problems
    1.88
     difficulties
    1.87
    Activations Density 1.672%

    No Known Activations