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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3189
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of context in understanding information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "put [something] in/into context" or similar constructions where information is being framed or explained within a broader perspective.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.51
    httphttps
    -0.48
    
    -0.46
    bitField
    -0.45
    Aiheesta
    -0.44
    SequentialGroup
    -0.44
    IsMutable
    -0.43
    borderSide
    -0.43
     astore
    -0.43
    routeProvider
    -0.40
    POSITIVE LOGITS
     context
    3.00
    context
    2.53
     Context
    2.50
     contexto
    2.34
     CONTEXT
    2.31
     контек
    2.30
    Context
    2.19
     contexts
    2.16
     Kontext
    2.16
     contextual
    2.13
    Activations Density 0.487%

    No Known Activations