© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 7048
    Prev
    Next
    INDEX
    Explanations

    syntax related to key-value pairs and structured data organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedArray
    -0.54
     sav
    -0.53
     zug
    -0.52
     ala
    -0.48
    rrggbb
    -0.47
     Forward
    -0.46
     front
    -0.46
    sav
    -0.46
    aves
    -0.46
    Forward
    -0.46
    POSITIVE LOGITS
    Билгалдахарш
    0.92
     الحره
    0.70
     Escolar
    0.67
     Jérusalem
    0.66
     umane
    0.65
    Hozzáférés
    0.65
     Allo
    0.64
    __':
    
    0.64
    nocache
    0.62
    SBATCH
    0.62
    Activations Density 0.056%

    No Known Activations