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. 41-GEMMASCOPE-RES-16K
    6. 10534
    Prev
    Next
    INDEX
    Explanations

    instances of scientific terminology and journal citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.56
     invokingState
    -0.55
     noDo
    -0.51
     TestBed
    -0.48
     صوتيه
    -0.47
    __(/*!
    -0.47
    Externé
    -0.47
     nonUne
    -0.47
     '\\;'
    -0.47
     presenter
    -0.46
    POSITIVE LOGITS
    IsMutable
    0.38
    disposing
    0.35
    ungkinan
    0.35
    cydow
    0.33
    .*")]
    0.33
    ngOnInit
    0.31
    writeFieldEnd
    0.31
     situ
    0.31
     Besøkt
    0.30
     ilman
    0.30
    Activations Density 0.717%

    No Known Activations