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. 2926
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and parameters, especially in relation to character encoding and configuration settings

    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
    ResumeLayout
    -1.16
    protoc
    -0.72
    DebuggerNonUser
    -0.66
    rxjs
    -0.56
    styleUrls
    -0.53
    Sqft
    -0.46
     skj
    -0.46
    ischen
    -0.44
     BoxDecoration
    -0.43
     aapt
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    3.68
    TagMode
    3.28
    SourceChecksum
    1.19
    Становништво
    1.08
    +#+#
    1.02
    ########.
    0.94
     مشين
    0.83
     disambiguazione
    0.78
    
    0.74
    ContentAlignment
    0.74
    Activations Density 0.012%

    No Known Activations