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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14866
    Prev
    Next
    INDEX
    Explanations

    terms associated with criminal activities, particularly extortion and abduction

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

    Following "to" or nouns related to extortion/demands

    np_acts-logits-general · gemini-2.0-flash

    demands for money or services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Includes
    -0.65
     include
    -0.65
    include
    -0.62
     inkluder
    -0.61
     includes
    -0.61
     included
    -0.61
    included
    -0.61
    Included
    -0.60
     Included
    -0.58
     Include
    -0.57
    POSITIVE LOGITS
     extortion
    1.19
     demands
    1.11
     demanding
    1.07
     demand
    1.06
     demanded
    1.00
    demand
    1.00
     Demands
    0.97
     blackmail
    0.97
    Demand
    0.94
     exige
    0.92
    Activations Density 0.187%

    No Known Activations