© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5252
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems and issues

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

    "problem" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Utilizamos
    -0.49
    /**
    -0.47
     kiedyś
    -0.47
    **
    
    -0.45
     libremente
    -0.44
     mandiri
    -0.44
    galus
    -0.44
     kepercayaan
    -0.44
     kehadiran
    -0.44
    Embrace
    -0.43
    POSITIVE LOGITS
     Problem
    1.20
     problem
    1.16
    Problem
    1.13
    problem
    1.12
     problems
    1.09
     PROBLEM
    1.08
     Problems
    1.01
    PROBLEM
    1.01
     Proble
    0.99
    problems
    0.98
    Activations Density 0.111%

    No Known Activations