Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11530
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities involved in legal cases and their associated actions

    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
     estekak
    -0.47
    fjspx
    -0.44
     IBOutlet
    -0.43
     noDo
    -0.40
    }`).
    -0.39
    Билгалдахарш
    -0.38
    er
    -0.37
    Còn
    -0.35
    сторія
    -0.35
    RectangleBorder
    -0.35
    POSITIVE LOGITS
    ized
    0.58
    ization
    0.52
     mxArray
    0.51
    ratic
    0.49
    kmal
    0.49
    󠁿
    0.49
    isation
    0.47
    izations
    0.46
    ordion
    0.46
    timedia
    0.45
    Activations Density 1.421%

    No Known Activations