© 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. 24-GEMMASCOPE-RES-16K
    11. 13755
    Prev
    Next
    INDEX
    Explanations

    terms related to HTTP request and response management

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

    HTTP headers and related terms

    np_acts-logits-general · gemini-2.0-flash

    HTTP headers, authorization, content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     footsteps
    -0.51
    érience
    -0.49
     wallet
    -0.48
    thâu
    -0.47
    achelor
    -0.47
    ähig
    -0.47
     initComponents
    -0.45
     voicing
    -0.45
    ighting
    -0.45
     wallets
    -0.45
    POSITIVE LOGITS
     headers
    1.30
     header
    1.25
     Headers
    1.14
     Header
    1.11
    header
    1.07
    headers
    1.07
    Header
    1.07
    Headers
    1.06
     HEADER
    0.91
     HEAD
    0.89
    Activations Density 0.506%

    No Known Activations