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. 10-GEMMASCOPE-RES-16K
    6. 2721
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.86
    yntaxException
    -0.83
    RectangleBorder
    -0.78
    发表于
    -0.76
    UserScript
    -0.75
     Gazetteer
    -0.72
     getItemId
    -0.72
    ]")]
    -0.71
    ConstraintMaker
    -0.70
    LLocation
    -0.68
    POSITIVE LOGITS
     voeten
    0.50
     gyóg
    0.46
     bouch
    0.46
     lenne
    0.46
    use
    0.46
     hombro
    0.46
     fejles
    0.45
    cektir
    0.45
     jellemző
    0.44
     ayak
    0.44
    Activations Density 0.760%

    No Known Activations