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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 5223
    Prev
    Next
    INDEX
    Explanations

    themes related to solitude and being alone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frattempo
    -0.88
    ofluorescence
    -0.69
     
    -0.67
     CURIAM
    -0.67
    WebControls
    -0.65
    yargs
    -0.63
    netinet
    -0.60
    írit
    -0.58
    ########.
    -0.57
     Ansch
    -0.56
    POSITIVE LOGITS
     Alone
    1.70
     ALONE
    1.65
     alone
    1.58
    alone
    1.55
    Alone
    1.46
     lonely
    1.28
     SOLO
    1.25
     solitary
    1.25
     lone
    1.24
     solo
    1.22
    Activations Density 0.058%

    No Known Activations