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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5754
    Prev
    Next
    INDEX
    Explanations

    references to the CIA and its operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.69
     MonoBehaviour
    -0.61
     unknownFields
    -0.60
     jsPsych
    -0.60
     sindaco
    -0.58
    principalTable
    -0.58
    prepareStatement
    -0.56
     GoFundMe
    -0.56
    feitura
    -0.55
    hdessä
    -0.54
    POSITIVE LOGITS
     intelligence
    1.48
    intelligence
    1.26
     Intelligence
    1.26
    Intelligence
    1.21
     spy
    1.21
     agents
    1.19
     CIA
    1.19
     secret
    1.15
     spies
    1.12
     agent
    1.12
    Activations Density 0.615%

    No Known Activations