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. 14-GEMMASCOPE-RES-16K
    6. 10561
    Prev
    Next
    INDEX
    Explanations

    closing braces in code syntax

    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
     doInBackground
    -0.79
     bezeichneter
    -0.70
     Cleo
    -0.66
    GEBURTSDATUM
    -0.66
    bigsqcup
    -0.66
     betweenstory
    -0.65
     Arc
    -0.64
     GenerationType
    -0.63
    ercises
    -0.62
    cifix
    -0.62
    POSITIVE LOGITS
    vode
    0.62
    LikeLike
    0.60
    ir
    0.60
    7
    0.59
    SuppressLint
    0.55
    kit
    0.54
    noindent
    0.54
    zer
    0.53
    3
    0.53
     Team
    0.53
    Activations Density 0.039%

    No Known Activations