Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1968
    Prev
    Next
    INDEX
    Explanations

    HTML tags with source (src) attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibol
    -0.48
    anso
    -0.47
    own
    -0.47
     organ
    -0.46
    once
    -0.45
    omba
    -0.45
    IFO
    -0.44
     Kowal
    -0.44
     hound
    -0.44
    ound
    -0.43
    POSITIVE LOGITS
     src
    1.82
    src
    1.70
    Src
    1.26
     Src
    1.13
     SRC
    1.02
    SRC
    0.91
     dst
    0.66
    srcs
    0.66
     AssemblyTitle
    0.63
    dst
    0.62
    Activations Density 0.054%

    No Known Activations