© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1278
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and phrases, particularly concerning data structures and memory layout

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

    Non-English language or code snippets

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     surla
    -0.45
     hObject
    -0.41
    ătoare
    -0.38
    └──
    -0.38
     dịch
    -0.36
    dịch
    -0.36
    ResponseCode
    -0.35
    ritsar
    -0.35
     chúa
    -0.35
     setObject
    -0.35
    POSITIVE LOGITS
     виправивши
    0.53
    Jereo
    0.50
    хьтан
    0.44
    Vtbl
    0.44
    SourceChecksum
    0.43
    BufferException
    0.43
    ConfigureAwait
    0.42
    jvm
    0.42
     compactness
    0.40
    Organisateur
    0.39
    Activations Density 0.321%

    No Known Activations