© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 657
    Prev
    Next
    INDEX
    Explanations

    references to scientific authors or their works

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

    names followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    <unused8>
    -0.81
    <unused41>
    -0.81
    <unused42>
    -0.80
    <unused23>
    -0.80
    <unused68>
    -0.80
    <unused43>
    -0.80
    <unused16>
    -0.80
    <unused51>
    -0.80
    <unused47>
    -0.80
    <unused14>
    -0.80
    POSITIVE LOGITS
    <eos>
    0.47
     Fürst
    0.38
     Roskov
    0.36
    HideFlags
    0.33
     vys
    0.31
     cited
    0.28
    cshtml
    0.28
     account
    0.28
    �
    0.28
    таратура
    0.27
    Activations Density 0.001%

    No Known Activations