© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 69405
    Prev
    Next
    INDEX
    Explanations

    references to vulnerability and weakness in context

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

    weak, vulnerability, predisposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.60
    AnimationsModule
    -0.53
     surla
    -0.52
    atguigu
    -0.46
     uLocal
    -0.45
     TextAppearance
    -0.43
    crollView
    -0.42
    MockMvc
    -0.42
     rosca
    -0.42
     begrü
    -0.42
    POSITIVE LOGITS
     weak
    2.02
    weak
    1.80
     Weak
    1.77
     weaker
    1.75
    Weak
    1.71
     fragile
    1.63
     weakness
    1.62
    弱
    1.58
     débil
    1.58
     weakest
    1.58
    Activations Density 0.209%

    No Known Activations