© 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. 24-GEMMASCOPE-RES-16K
    6. 678
    Prev
    Next
    INDEX
    Explanations

    references to mobile research methodologies

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

    Code, math, and table syntax

    np_acts-logits-general · gemini-2.0-flash

    data entries and lists

    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
    Personendaten
    -0.88
     كومونز
    -0.70
     autorytatywna
    -0.70
    +#+
    -0.69
    sizeCache
    -0.68
     snippetHide
    -0.66
     <<<<<<<<<<<<<<
    -0.64
    存于互联网档案馆
    -0.64
     للمعارف
    -0.63
    Datuak
    -0.60
    POSITIVE LOGITS
     etc
    0.50
    etc
    0.46
     and
    0.45
     these
    0.45
     plus
    0.44
     neither
    0.42
    ed
    0.42
     hatta
    0.42
     screen
    0.41
     serta
    0.41
    Activations Density 1.163%

    No Known Activations