© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    phrases indicating joint participation and collaboration

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

    references to parents or parental involvement in activities.

    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
     rekke
    -0.32
     владе
    -0.31
     Grund
    -0.29
    ly
    -0.28
     
    -0.28
     bypassing
    -0.27
     reputations
    -0.27
     Gegen
    -0.27
     applied
    -0.27
     setup
    -0.27
    POSITIVE LOGITS
    ########.
    0.72
     companion
    0.71
     towarzys
    0.70
     companions
    0.69
    RegistryLite
    0.68
    partner
    0.67
    脚注の使い方
    0.67
     CreateTagHelper
    0.66
    companion
    0.66
    一起
    0.66
    Activations Density 0.205%

    No Known Activations