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. 4346
    Prev
    Next
    INDEX
    Explanations

    complex clauses and nested structures in sentences

    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
    .
    -0.79
    。
    -0.73
    ).
    -0.72
    ].
    -0.63
    ."
    -0.63
    }.
    -0.62
    }$.
    -0.62
    ».
    -0.60
    $.
    -0.60
    .</
    -0.59
    POSITIVE LOGITS
     CreateTagHelper
    0.98
    Архівовано
    0.84
    ConstraintMaker
    0.79
    elemField
    0.79
     EconPapers
    0.78
    verwijspagina
    0.78
    LookAnd
    0.78
     Paglinawan
    0.76
     كومونز
    0.75
    IndentedString
    0.74
    Activations Density 0.565%

    No Known Activations