© 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. 31-GEMMASCOPE-RES-16K
    11. 8375
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-identity and personal assertion

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

    phrases that express existential or identity-based questions about who someone is or what defines them.

    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
    évaluateur
    -0.47
     Roskov
    -0.44
     CreateTagHelper
    -0.41
    GTCX
    -0.40
     defaultstate
    -0.40
    TagHelper
    -0.40
     OnTriggerEnter
    -0.39
     joaat
    -0.38
    日閲覧
    -0.36
     strerror
    -0.36
    POSITIVE LOGITS
     somos
    0.86
    我们是
    0.84
     jesteśmy
    0.83
    我是
    0.81
     jestem
    0.74
    自己是
    0.73
     estamos
    0.73
     jesteś
    0.71
     siamo
    0.70
     youre
    0.64
    Activations Density 0.295%

    No Known Activations