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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13488
    Prev
    Next
    INDEX
    Explanations

    terms related to credit and financial services for individuals with poor credit ratings

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

    financial or transactional language involving loans, payments, and credit services.

    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
    PRNewswire
    -0.52
     daß
    -0.45
    complexType
    -0.44
    #+#
    -0.42
    Vidite
    -0.42
    principalColumn
    -0.41
     coworker
    -0.40
    StoryboardSegue
    -0.40
     roadways
    -0.40
    OGND
    -0.40
    POSITIVE LOGITS
     spoilt
    0.62
     learnt
    0.62
     envisaged
    0.57
     commonest
    0.57
     characterised
    0.56
     tonnes
    0.56
     hence
    0.56
     availed
    0.54
     Uganda
    0.54
     artistes
    0.54
    Activations Density 0.426%

    No Known Activations