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

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 9561
    Prev
    Next
    INDEX
    Explanations

    issues and challenges people face in various situations

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

    Troubleshooting a problem or issue

    np_acts-logits-general · gemini-2.0-flash

    encountering difficulties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gweler
    -0.54
    <_>
    -0.47
    Sucesor
    -0.44
    Према
    -0.43
    хьтан
    -0.41
    (&:
    -0.40
     سكانية
    -0.40
    enumi
    -0.38
    erequisite
    -0.38
    inheritDoc
    -0.37
    POSITIVE LOGITS
     getting
    0.84
     finding
    0.81
     installing
    0.80
     managing
    0.77
     communicating
    0.75
     adjusting
    0.74
     accessing
    0.73
     organizing
    0.72
     dealing
    0.72
     establishing
    0.71
    Activations Density 0.289%

    No Known Activations