© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8000
    Prev
    Next
    INDEX
    Explanations

    terms related to corporate auditing and financial structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.42
    UnusedPrivate
    -0.40
    AddTagHelper
    -0.40
    IntoConstraints
    -0.38
    makedirs
    -0.36
    optionalTypeArgs
    -0.35
    StackNavigator
    -0.35
    NewUrlParser
    -0.34
    SequentialGroup
    -0.34
     RouterModule
    -0.33
    POSITIVE LOGITS
     consulting
    2.52
     consultancy
    2.38
     consultants
    2.33
     consultant
    2.28
    consult
    2.23
     consult
    2.19
    consulting
    2.16
     CONSULT
    2.11
     Consulting
    2.09
    Consulting
    2.09
    Activations Density 0.456%

    No Known Activations