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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 15165
    Prev
    Next
    INDEX
    Explanations

    assertions of territorial or jurisdictional claims

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

    contested territorial claims and disputes over sovereignty.

    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
    abstractmethod
    -0.40
    ImageContext
    -0.40
     SDLK
    -0.37
    الحياه
    -0.36
     onPostExecute
    -0.36
    اعد
    -0.35
     gydy
    -0.35
     poffible
    -0.35
    Moder
    -0.34
     sumpay
    -0.34
    POSITIVE LOGITS
     claim
    1.56
     Claim
    1.42
     claimed
    1.38
     claiming
    1.38
    claim
    1.37
     claims
    1.36
     CLAIM
    1.35
    Claim
    1.30
     Claims
    1.21
     territorial
    1.16
    Activations Density 0.514%

    No Known Activations