© 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. 539
    Prev
    Next
    INDEX
    Explanations

    parts of the text related to reading experiences and storytelling elements

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

    permanent and irreversible outcomes

    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
     itſelf
    -0.52
     ſtill
    -0.48
    djangoproject
    -0.47
     myſelf
    -0.46
     reaſon
    -0.45
     neceſſ
    -0.45
    utilisons
    -0.45
     Taktlose
    -0.44
     themſelves
    -0.44
    ambién
    -0.43
    POSITIVE LOGITS
     permanent
    0.56
     Permanent
    0.56
     permanently
    0.53
     never
    0.51
    perman
    0.50
     PERMAN
    0.50
    Permanent
    0.49
     irreversible
    0.47
    permanent
    0.47
     навсегда
    0.47
    Activations Density 0.072%

    No Known Activations