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. 12-GEMMASCOPE-RES-16K
    6. 6492
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional or psychological states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )':
    -0.61
    ]**
    -0.57
    reggio
    -0.54
    seende
    -0.52
     AppModule
    -0.51
    mapStateToProps
    -0.51
    μον
    -0.50
    )":
    -0.50
    meable
    -0.49
     betreft
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.70
     gynhyrchwyd
    0.68
    脚注の使い方
    0.62
     Walkover
    0.59
    Personensuche
    0.57
     Occur
    0.56
     виправивши
    0.54
    IntoConstraints
    0.53
    Билгалдахарш
    0.50
     bear
    0.50
    Activations Density 0.883%

    No Known Activations