© 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 EvalsExportsinterp-engineNEWAPI 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. 9130
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between concepts or entities

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

    "in", "which", "that", followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    which in turn

    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
    گاب
    -0.44
     MwSt
    -0.40
    böz
    -0.40
     Normdatei
    -0.39
    __))
    -0.37
    ↹
    -0.35
     dans
    -0.35
     Museum
    -0.35
     Grimal
    -0.35
    Nella
    -0.34
    POSITIVE LOGITS
     wiederum
    1.28
     turn
    1.07
     kolei
    0.94
     subsequently
    0.91
     consequently
    0.86
     ultimately
    0.84
    turn
    0.83
     बद
    0.79
     Turn
    0.78
    Turn
    0.77
    Activations Density 0.444%

    No Known Activations