© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9582
    Prev
    Next
    INDEX
    Explanations

    legal terminology and conditions related to usage rights and responsibilities

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

    legal and licensing disclaimers, terms of service, and copyright notices.

    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
     forgets
    -0.45
     contradicted
    -0.45
     olan
    -0.45
     dourada
    -0.45
     sympathize
    -0.44
     forbids
    -0.44
     Barros
    -0.43
     modernize
    -0.43
     doubted
    -0.43
     contradicts
    -0.43
    POSITIVE LOGITS
     ujednoznacz
    0.75
     EconPapers
    0.75
    MigrationBuilder
    0.60
     disambiguazione
    0.58
    SequentialGroup
    0.57
    AnchorStyles
    0.54
    AISSEE
    0.51
     kasarigan
    0.50
    IsMutable
    0.50
    #+#
    0.49
    Activations Density 0.726%

    No Known Activations