© 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. 31-GEMMASCOPE-RES-16K
    6. 11962
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and community advocacy

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

    pronouns and determiners referring to people who deserve recognition or merit acknowledgment.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    위
    -0.37
     Task
    -0.33
    addTask
    -0.32
     incor
    -0.32
    })+
    -0.32
    Poss
    -0.31
     Tand
    -0.31
     proble
    -0.30
     posi
    -0.30
     kil
    -0.30
    POSITIVE LOGITS
     deserve
    2.14
     deserves
    2.11
     deserved
    1.80
     deserving
    1.78
     mérit
    1.49
     verdient
    1.44
     mérite
    1.40
    deserved
    1.39
     merits
    1.32
     merece
    1.26
    Activations Density 0.307%

    No Known Activations