Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12902
    Prev
    Next
    INDEX
    Explanations

    questions or statements related to mathematical calculations and factorization

    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
    ptid
    -0.58
     <<<<<<<<<<<<<<
    -0.56
    __':
    
    -0.54
     moro
    -0.53
    };*/
    -0.53
     createTime
    -0.52
    }`).
    -0.50
    hassee
    -0.49
    Решение
    -0.49
     Lorde
    -0.48
    POSITIVE LOGITS
     the
    0.94
     our
    0.82
     their
    0.77
     صوتيه
    0.77
    ValueStyle
    0.74
     your
    0.71
    GraphicsUnit
    0.68
    NameInMap
    0.68
    ंदीखरीदारी
    0.63
     its
    0.62
    Activations Density 0.338%

    No Known Activations