© 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. 20-GEMMASCOPE-RES-16K
    11. 4008
    Prev
    Next
    INDEX
    Explanations

    terms related to methods and strategies in various contexts

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

    technical terminology and methodological language across different domains like technology, research, and education.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $_(
    -0.49
    moveToFirst
    -0.47
    лтемелер
    -0.47
     queſta
    -0.45
     craters
    -0.44
     πλη
    -0.44
    writeField
    -0.44
     Volley
    -0.44
    URLException
    -0.44
     Numerade
    -0.44
    POSITIVE LOGITS
     methods
    1.22
     techniques
    1.13
     method
    1.09
    methods
    1.05
     méthodes
    1.04
     Methoden
    1.02
     método
    1.00
     métodos
    0.99
     metode
    0.99
     Methods
    0.97
    Activations Density 0.457%

    No Known Activations