© 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. 2-GEMMASCOPE-RES-16K
    6. 8219
    Prev
    Next
    INDEX
    Explanations

    instances of the root "res" in different contexts, particularly in relation to 'resolution' or 'response.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.42
    GEBURTS
    -0.40
    SocketChannel
    -0.40
    LookAnd
    -0.39
    utilisons
    -0.38
    WriteLiteral
    -0.37
    TagMode
    -0.36
    हित
    -0.36
     apor
    -0.35
    ंदीखरीदारी
    -0.34
    POSITIVE LOGITS
     Res
    3.55
    Res
    3.34
     res
    3.27
     RES
    3.00
    res
    2.72
    RES
    2.66
     rés
    2.16
     resi
    1.98
     Rés
    1.91
     rese
    1.86
    Activations Density 0.297%

    No Known Activations