© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4921
    Prev
    Next
    INDEX
    Explanations

    sentences discussing the impact and influence of individuals or results in a specific field

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

    Follows "Q:" (likely questions)

    np_acts-logits-general · gemini-2.0-flash

    promulgated proposals and discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useAuth
    -0.56
     morire
    -0.53
     innamor
    -0.53
    noinspection
    -0.52
    โก
    -0.51
     restTemplate
    -0.50
     GetComponent
    -0.50
     propTypes
    -0.49
     images
    -0.49
     eccell
    -0.49
    POSITIVE LOGITS
    contentLoaded
    0.74
     regulatory
    0.74
     promulgated
    0.71
     discussions
    0.67
     discussion
    0.67
     proposal
    0.66
     promul
    0.66
     promulg
    0.66
     contentious
    0.65
     proposals
    0.65
    Activations Density 0.464%

    No Known Activations