© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3270
    Prev
    Next
    INDEX
    Explanations

    expressions related to financial risks and economic instability

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

    phrases related to political and power dynamics, especially involving complex bureaucratic or governmental systems.

    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
    ighed
    -0.46
    mybatisplus
    -0.44
     Explor
    -0.44
    igua
    -0.40
    🇶
    -0.40
    leven
    -0.39
    httphttps
    -0.39
     carriers
    -0.39
     Topic
    -0.38
     Adults
    -0.38
    POSITIVE LOGITS
    脚注の使い方
    0.51
     StatelessWidget
    0.50
    AddTagHelper
    0.49
    AndroidJUnit
    0.48
     Administrativna
    0.47
    CHAFT
    0.46
     CWE
    0.46
     ✭✭
    0.44
    InputBorder
    0.44
     kill
    0.43
    Activations Density 0.445%

    No Known Activations