© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 174
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or markers in structured data or programming syntax

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

    Code, formatting, or programming-related content

    np_acts-logits-general · gemini-2.0-flash

    ocyte function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     sum
    -0.49
     all
    -0.45
     most
    -0.45
     above
    -0.45
     –
    -0.44
     prime
    -0.44
     technically
    -0.44
     dynamically
    -0.44
     make
    -0.43
     —
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.88
    ंदीखरीदारी
    0.86
     CreateTagHelper
    0.85
    '},
    0.85
    '));
    0.83
     '\\;'
    0.83
    ")));
    0.81
     MonoBehaviour
    0.81
    SequentialGroup
    0.81
     صوتيه
    0.80
    Activations Density 0.025%

    No Known Activations