© 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. 28-GEMMASCOPE-RES-16K
    6. 3904
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms associated with measurement and data processing

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

    preceding a period

    np_acts-logits-general · gemini-2.0-flash

    technical concepts and their properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.63
    #+#
    -0.51
     propOrder
    -0.48
    expandindo
    -0.47
     CreateTagHelper
    -0.46
    DockStyle
    -0.44
    seamnă
    -0.44
    حياته
    -0.43
    ünkü
    -0.41
    (!__
    -0.41
    POSITIVE LOGITS
     efficiently
    0.73
     quickly
    0.65
     without
    0.65
     using
    0.63
     automatically
    0.60
     instantaneously
    0.59
    quickly
    0.57
     pomocou
    0.57
     remotely
    0.56
    without
    0.56
    Activations Density 1.023%

    No Known Activations