© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6205
    Prev
    Next
    INDEX
    Explanations

    the word "von" and its variations, indicating a focus on proper names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.40
    Atoi
    -0.34
     TextAlign
    -0.33
     špat
    -0.33
     umsch
    -0.33
    flasche
    -0.32
    omega
    -0.32
     expressão
    -0.32
    $('.
    -0.31
     determinación
    -0.31
    POSITIVE LOGITS
     von
    1.18
    Von
    1.06
     Von
    1.02
     VON
    1.00
    von
    0.93
    VON
    0.89
    balleur
    0.56
    MLLoader
    0.56
     MotionEvent
    0.55
     Freih
    0.54
    Activations Density 0.037%

    No Known Activations