© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84762
    Prev
    Next
    INDEX
    Explanations

    terms related to the mining process and technology of cryptocurrencies

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

    cryptocurrency mining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Autowired
    -0.48
    pax
    -0.46
    arach
    -0.46
     spring
    -0.44
    ligator
    -0.42
    liferay
    -0.42
    AnchorStyles
    -0.42
    esgue
    -0.41
    fas
    -0.41
    scalatest
    -0.40
    POSITIVE LOGITS
     mining
    0.47
    MessageTagHelper
    0.47
     auroit
    0.46
     miners
    0.45
     Mining
    0.45
     Offisielt
    0.44
    Mining
    0.44
    mining
    0.44
    lindungan
    0.42
     MINING
    0.42
    Activations Density 0.004%

    No Known Activations