© 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. 34-GEMMASCOPE-RES-16K
    6. 11276
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and details related to a murder investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AISSEE
    -0.55
     tag
    -0.45
    tag
    -0.44
     Crush
    -0.43
    zey
    -0.42
    TableHead
    -0.42
     tiguan
    -0.41
     tagging
    -0.41
    numerusform
    -0.41
     fusil
    -0.40
    POSITIVE LOGITS
     holster
    0.64
     concealed
    0.54
     Glock
    0.52
     EDC
    0.49
     handgun
    0.48
     Conce
    0.47
     concealment
    0.47
    Conce
    0.45
     draw
    0.45
     draws
    0.44
    Activations Density 0.091%

    No Known Activations