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. 2675
    Prev
    Next
    INDEX
    Explanations

    statements about the presence or existence of various options or benefits

    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
    GEBURTSDATUM
    -0.83
    routeProvider
    -0.71
    }$.\\
    -0.71
     vPvB
    -0.69
     lenker
    -0.68
    }}$\\
    -0.68
    ngua
    -0.67
    Rohy
    -0.67
    Demografie
    -0.65
    Демографія
    -0.63
    POSITIVE LOGITS
     Eſ
    0.52
    selves
    0.50
    MERCIAL
    0.50
    ebenarnya
    0.46
    volvement
    0.46
    ITERATURE
    0.46
    ÁB
    0.45
    bila
    0.45
     Bé
    0.45
    ENEFITS
    0.45
    Activations Density 0.429%

    No Known Activations