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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5555
    Prev
    Next
    INDEX
    Explanations

    references to challenging or difficult truths and issues that require confrontation

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

    Difficult or inconvenient truths/issues

    np_acts-logits-general · gemini-2.0-flash

    difficult or unpleasant truths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.62
     Roskov
    -0.57
    tagHelperRunner
    -0.57
     '\\;'
    -0.56
    URLException
    -0.54
     BoxFit
    -0.53
     vainilla
    -0.52
     consultato
    -0.52
    elemField
    -0.51
     ſta
    -0.51
    POSITIVE LOGITS
     unpopular
    0.56
     unpleasant
    0.49
     uncomfortable
    0.46
     tough
    0.43
     difficulty
    0.40
    difficulty
    0.39
     difficult
    0.39
     inconvenient
    0.38
    Difficult
    0.37
    Tough
    0.37
    Activations Density 0.378%

    No Known Activations