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. 7-GEMMASCOPE-RES-16K
    6. 15556
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "bring" and related actions indicating the act of introducing or contributing to something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.65
    ſelves
    -0.60
    ukkig
    -0.58
    ſelf
    -0.57
    pausal
    -0.56
    CellStyle
    -0.53
     ſche
    -0.53
    AndEndTag
    -0.52
     estekak
    -0.52
     Femin
    -0.51
    POSITIVE LOGITS
     bring
    2.16
     Bring
    2.14
    Bring
    2.06
    bring
    1.98
     Bringing
    1.98
     bringing
    1.95
     brings
    1.95
     brought
    1.95
    Bringing
    1.92
    brought
    1.84
    Activations Density 0.067%

    No Known Activations