© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5471
    Prev
    Next
    INDEX
    Explanations

    numerical data and related operations

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

    Numerical counts or indices

    np_acts-logits-general · gemini-2.0-flash

    counts or parameters

    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
     queſta
    -1.20
     témoig
    -1.18
     ſei
    -1.14
     beſte
    -1.13
     MainAxisSize
    -1.12
     zwiſchen
    -1.12
    migrationBuilder
    -1.10
    <unused52>
    -1.09
    <unused16>
    -1.09
    <unused8>
    -1.09
    POSITIVE LOGITS
    3
    0.40
    7
    0.40
    2
    0.39
    4
    0.39
    5
    0.39
    0
    0.37
    1
    0.36
    6
    0.35
    8
    0.35
    9
    0.34
    Activations Density 1.227%

    No Known Activations