© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15121
    Prev
    Next
    INDEX
    Explanations

    expressive emotional responses and exclamatory phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    emphatic statements and declarations expressed in all capital letters.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̈́
    -0.44
     MessageBoxIcon
    -0.37
    的结果
    -0.36
    udios
    -0.33
    ContentAlignment
    -0.33
    BufferException
    -0.32
     InputDecoration
    -0.32
    sproz
    -0.32
    ituary
    -0.31
     OMIT
    -0.31
    POSITIVE LOGITS
     nakalista
    0.76
    /**
    0.68
    Aholisi
    0.62
     Púb
    0.59
    таратура
    0.58
     çekilen
    0.55
    Demografía
    0.55
    @[+][
    0.55
    antd
    0.54
     yapılan
    0.54
    Activations Density 2.495%

    No Known Activations